© 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. 14045
    Prev
    Next
    INDEX
    Explanations

    references to the Atari gaming console

    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
    27
    +0.03
    0.5%
    226
    +0.03
    0.4%
    440
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.03
    0.01
    612
    +0.03
    0.01
    596
    +0.03
    0.00
    Negative Logits
    merce
    -0.27
    nces
    -0.26
    zag
    -0.25
    EStream
    -0.24
    uchin
    -0.24
     arrang
    -0.24
    resy
    -0.24
    idy
    -0.24
    Ħ¢
    -0.23
    gement
    -0.23
    POSITIVE LOGITS
     CTR
    0.24
     Colo
    0.24
     Ether
    0.23
     tel
    0.22
     Citadel
    0.22
     CrossRef
    0.22
     Lith
    0.21
     Recomm
    0.21
     Elixir
    0.20
     mart
    0.20
    Activations Density 0.004%

    No Known Activations