© 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. 14687
    Prev
    Next
    INDEX
    Explanations

    references to space missions and space stations

    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
    267
    +0.13
    0.5%
    70
    +0.13
    0.4%
    366
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.06
    149
    +0.13
    0.03
    708
    +0.12
    0.03
    Negative Logits
    aciously
    -1.08
     Keeper
    -0.89
     Reach
    -0.89
    endish
    -0.84
    Legend
    -0.83
    arium
    -0.82
    acious
    -0.81
    ENTION
    -0.81
    href
    -0.81
    Oak
    -0.77
    POSITIVE LOGITS
    sts
    1.68
    tics
    1.47
    tic
    1.29
    zing
    1.26
    zed
    1.25
    zer
    1.23
    tical
    1.17
    pse
    1.15
    zers
    1.14
    zes
    1.04
    Activations Density 0.812%

    No Known Activations