© 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. 46059
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions

    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
    99
    +0.17
    0.8%
    447
    +0.16
    0.8%
    276
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.17
    0.52
    138
    +0.16
    0.49
    64
    +0.11
    -0.24
    Negative Logits
    dyl
    -0.82
    rieved
    -0.80
    ODUCT
    -0.77
    rican
    -0.77
    abies
    -0.77
    ivated
    -0.76
    utterstock
    -0.76
    ģĸ
    -0.76
    awaru
    -0.75
    ortality
    -0.74
    POSITIVE LOGITS
    phrine
    1.51
    lla
    1.16
    jad
    1.05
    lihood
    1.00
    llo
    0.96
    lli
    0.90
    hart
    0.88
    backer
    0.81
    clude
    0.76
    apple
    0.73
    Activations Density 17.239%

    No Known Activations