© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2940
    Prev
    Next
    INDEX
    Explanations

    expressions mentioning two or three options or possibilities

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    416
    +0.04
    0.5%
    209
    +0.03
    0.4%
    274
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    656
    +0.04
    0.03
    748
    +0.03
    0.03
    327
    +0.03
    0.03
    Negative Logits
    âĢİ
    -0.25
    MSN
    -0.24
    anse
    -0.22
     Dise
    -0.22
    ITNESS
    -0.21
     Akin
    -0.21
    MET
    -0.20
    sold
    -0.20
    Unity
    -0.20
    ampions
    -0.20
    POSITIVE LOGITS
     guesses
    0.24
     choices
    0.22
     summers
    0.21
     worldview
    0.21
    rax
    0.21
     options
    0.21
    ado
    0.21
    +.
    0.20
     collar
    0.20
     nose
    0.20
    Activations Density 0.109%

    No Known Activations