© 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. 14238
    Prev
    Next
    INDEX
    Explanations

    discussion about sports teams, players, games, strategies, and potential changes in personnel

    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
    696
    +0.18
    0.6%
    393
    +0.15
    0.5%
    535
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.18
    0.06
    636
    +0.15
    0.05
    637
    +0.14
    0.05
    Negative Logits
    ulhu
    -1.13
    ļéĨĴ
    -1.02
    minster
    -1.01
    CVE
    -1.00
    acci
    -0.99
    aez
    -0.94
    culated
    -0.94
    Export
    -0.93
    raham
    -0.92
    iard
    -0.89
    POSITIVE LOGITS
     coasts
    1.18
    earth
    1.17
     coast
    1.15
    fen
    1.09
    shoot
    1.06
    balance
    1.03
     ledge
    0.99
     shores
    0.98
    ilts
    0.97
     limb
    0.96
    Activations Density 0.821%

    No Known Activations