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

    Neuronpedia

    Jacobian LensNEW
    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. 800
    Prev
    Next
    INDEX
    Explanations

    references to a particular individual or cause, likely related to activism or social justice

    oai_token-act-pair · gpt-3.5-turbo
    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
    450
    +0.16
    0.5%
    71
    +0.15
    0.5%
    218
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.16
    0.04
    218
    +0.15
    0.04
    90
    +0.14
    0.04
    Negative Logits
    çīĪ
    -1.11
    hack
    -0.98
    raid
    -0.97
    venture
    -0.96
    cript
    -0.95
    eri
    -0.94
    æĸ¹
    -0.90
    elled
    -0.90
    ENG
    -0.88
    puff
    -0.88
    POSITIVE LOGITS
     adulthood
    0.90
     AFTER
    0.88
    atcher
    0.88
    iversal
    0.86
     shore
    0.85
    terday
    0.84
    unda
    0.84
     proven
    0.84
     they
    0.84
     someone
    0.83
    Activations Density 0.293%

    No Known Activations