© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13599
    Prev
    Next
    INDEX
    Explanations

    references to the ancient civilization of Mesopotamia

    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
    351
    +0.16
    0.6%
    649
    +0.14
    0.6%
    288
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.07
    326
    +0.14
    0.05
    464
    +0.13
    0.04
    Negative Logits
    ICE
    -0.94
    cake
    -0.79
     Bleach
    -0.79
    èª
    -0.74
    pedia
    -0.73
     ObamaCare
    -0.72
    acies
    -0.71
    inition
    -0.71
    insured
    -0.70
    butt
    -0.70
    POSITIVE LOGITS
    opot
    1.31
    quite
    1.26
    olithic
    1.06
    gon
    0.99
    earchers
    0.97
    bows
    0.97
    nil
    0.93
     Mes
    0.93
    meric
    0.92
    asonic
    0.92
    Activations Density 0.545%

    No Known Activations