© 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. 12613
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to leadership positions in various organizations

    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
    167
    +0.12
    0.6%
    104
    +0.12
    0.5%
    91
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.12
    0.11
    204
    +0.12
    0.10
    146
    +0.11
    0.11
    Negative Logits
    lez
    -0.66
    schild
    -0.65
     incarcer
    -0.63
    illance
    -0.62
    itten
    -0.62
     impoverished
    -0.60
    DonaldTrump
    -0.60
     Newsp
    -0.58
     underdog
    -0.57
     cruc
    -0.57
    POSITIVE LOGITS
    ials
    0.92
    chief
    0.90
    IAL
    0.86
    esses
    0.85
    ially
    0.85
    rors
    0.84
     emer
    0.77
    rators
    0.74
     overseeing
    0.73
    ial
    0.73
    Activations Density 2.786%

    No Known Activations