© 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. 11209
    Prev
    Next
    INDEX
    Explanations

    language related to social engagement and online sharing

    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
    679
    +0.19
    0.7%
    68
    +0.13
    0.5%
    39
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.19
    0.05
    185
    +0.13
    0.04
    74
    +0.12
    0.04
    Negative Logits
    schild
    -1.07
    olit
    -0.91
    undai
    -0.90
    panic
    -0.90
    anwhile
    -0.89
    gm
    -0.87
    paio
    -0.87
    sbm
    -0.87
     compr
    -0.86
    annis
    -0.85
    POSITIVE LOGITS
    holders
    1.43
    holder
    1.35
    ership
    1.18
    ables
    1.11
    Tweet
    1.01
    cro
    1.00
    edin
    0.98
     Share
    0.95
    able
    0.93
    ability
    0.93
    Activations Density 0.560%

    No Known Activations