© 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. 2698
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details, possibly related to engineering or products

    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
    651
    +0.20
    0.7%
    336
    +0.16
    0.5%
    259
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.20
    0.06
    651
    +0.16
    0.06
    336
    +0.15
    0.04
    Negative Logits
    ¥ŀ
    -1.11
    NetMessage
    -1.06
     destro
    -1.04
     confir
    -1.00
    ©¶æ
    -0.98
     schooling
    -0.96
     therap
    -0.94
    ´
    -0.92
    EStream
    -0.92
    cknow
    -0.90
    POSITIVE LOGITS
    uary
    1.60
    amins
    1.43
    ocracy
    1.40
    chell
    1.40
    unes
    1.37
    anium
    1.35
    igation
    1.32
    onal
    1.31
    arius
    1.28
    chers
    1.26
    Activations Density 1.692%

    No Known Activations