© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13140
    Prev
    Next
    INDEX
    Explanations

    terms related to human evolution

    oai_token-act-pair · gpt-3.5-turbo

    words associated with the term "human" or its derivatives (e.g., "Transhumanist", "Posthumans")

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.10
    0.5%
    583
    +0.08
    0.4%
    649
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.06
    365
    +0.08
    0.03
    93
    +0.08
    0.03
    Negative Logits
    NEY
    -0.71
    REL
    -0.59
    ieri
    -0.58
    76561
    -0.56
    leeve
    -0.53
    BALL
    -0.52
     brim
    -0.52
     connecting
    -0.52
    bery
    -0.51
     disagree
    -0.51
    POSITIVE LOGITS
    ity
    0.94
    itarian
    0.93
    nesses
    0.79
    ciating
    0.77
    icz
    0.76
    ukong
    0.75
    ities
    0.73
    humans
    0.72
    zees
    0.71
    itary
    0.70
    Activations Density 0.374%

    No Known Activations