© 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 Local
    5. 6-RES_SCL-AJT
    6. 46040
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions and legislation

    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
    285
    +0.14
    0.6%
    247
    +0.12
    0.5%
    569
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.14
    0.08
    103
    +0.12
    0.10
    151
    +0.12
    0.14
    Negative Logits
    anwhile
    -0.99
    ral
    -0.80
    ModLoader
    -0.80
     McCann
    -0.76
    redients
    -0.75
    perty
    -0.73
     Crusader
    -0.71
     Gutenberg
    -0.71
    zee
    -0.71
    ebook
    -0.69
    POSITIVE LOGITS
    ocated
    1.17
    ocate
    1.15
    ocation
    1.06
    apse
    0.96
    ubric
    0.95
    ikes
    0.93
    oved
    0.93
    ocker
    0.90
    ateral
    0.90
    odge
    0.89
    Activations Density 6.131%

    No Known Activations