© 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 EvalsExportsinterp-engineNEWAPI 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. 8543
    Prev
    Next
    INDEX
    Explanations

    verbal expressions related to taking care of someone or something

    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
    507
    +0.11
    0.5%
    607
    +0.11
    0.5%
    108
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.10
    59
    +0.11
    0.06
    350
    +0.10
    0.07
    Negative Logits
    sonian
    -0.81
    likely
    -0.76
    zai
    -0.74
     sidx
    -0.74
    ultane
    -0.72
    assic
    -0.70
    anian
    -0.67
    hler
    -0.67
     weighted
    -0.66
    ueller
    -0.66
    POSITIVE LOGITS
     him
    1.04
     them
    0.93
     orphans
    0.83
     Compan
    0.82
    him
    0.80
     children
    0.76
     livestock
    0.73
     themselves
    0.72
     herself
    0.71
     himself
    0.71
    Activations Density 1.607%

    No Known Activations