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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14137
    Prev
    Next
    INDEX
    Explanations

    informational references or indirect mentions within a context of dialogue or narration

    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
    393
    +0.26
    1.2%
    362
    +0.13
    0.6%
    689
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.26
    0.09
    362
    +0.13
    0.10
    393
    +0.10
    0.12
    Negative Logits
    FIG
    -0.70
     Zup
    -0.69
    poons
    -0.68
    viks
    -0.68
    encia
    -0.68
    aneers
    -0.68
    icone
    -0.66
    thouse
    -0.66
    vl
    -0.65
    pload
    -0.65
    POSITIVE LOGITS
     impending
    0.96
     upcoming
    0.89
     specific
    0.89
     particular
    0.88
     topic
    0.85
     specifics
    0.85
     hypothetical
    0.84
     happening
    0.80
     pesky
    0.80
     topics
    0.79
    Activations Density 1.690%

    No Known Activations