© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 4871
    Prev
    Next
    INDEX
    Explanations

    numerical patterns or codes embedded in long strings of text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    326
    +0.14
    0.7%
    447
    +0.13
    0.7%
    464
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.20
    93
    +0.13
    0.07
    472
    +0.10
    0.05
    Negative Logits
    lihood
    -0.70
    hold
    -0.68
    ãĥĢ
    -0.67
     Luthor
    -0.65
    EngineDebug
    -0.64
     Lazarus
    -0.64
    FontSize
    -0.61
     Jol
    -0.60
    tenance
    -0.59
    ously
    -0.59
    POSITIVE LOGITS
    ategory
    1.52
    kefeller
    0.96
    ombat
    0.94
    urrency
    0.94
    elsius
    0.93
    urrencies
    0.86
    ycle
    0.85
    arthy
    0.84
    QB
    0.83
    orsi
    0.79
    Activations Density 7.340%

    No Known Activations