© 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 Local
    9. 6-RES_SCL-AJT
    11. 33459
    Prev
    Next
    INDEX
    Explanations

    specific locations or regions

    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
    430
    +0.10
    0.5%
    623
    +0.10
    0.5%
    253
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.10
    0.07
    585
    +0.10
    0.10
    701
    +0.09
    0.06
    Negative Logits
    ulating
    -0.92
    ulated
    -0.85
    ulators
    -0.82
    ulates
    -0.81
    ulation
    -0.80
    sters
    -0.77
    ulations
    -0.76
    ulate
    -0.74
    ulator
    -0.73
    ulatory
    -0.72
    POSITIVE LOGITS
     Territories
    0.77
     Than
    0.75
    burgh
    0.72
    Th
    0.72
     Greater
    0.69
     Dimensions
    0.69
     Neigh
    0.68
     Regional
    0.68
     Heights
    0.68
     Lakes
    0.67
    Activations Density 6.267%

    No Known Activations