© 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 EvalsExportsAPI 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. 12036
    Prev
    Next
    INDEX
    Explanations

    text related to image credits and attributions

    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
    679
    +0.22
    0.7%
    498
    +0.15
    0.5%
    739
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.22
    0.03
    326
    +0.15
    0.04
    609
    +0.14
    0.03
    Negative Logits
    akia
    -1.30
    lear
    -1.23
    thin
    -1.21
    aqu
    -1.18
    sil
    -1.13
    ylum
    -1.12
    atform
    -1.10
    ullivan
    -1.08
    olver
    -1.07
    ulz
    -1.07
    POSITIVE LOGITS
    tesy
    1.47
     courtesy
    1.11
     Credit
    1.00
     attribution
    0.99
    assetsadobe
    0.97
     Thomson
    0.96
     Wikimedia
    0.95
    giving
    0.94
     Dragonbound
    0.93
     Grab
    0.93
    Activations Density 0.487%

    No Known Activations