© 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. 40695
    Prev
    Next
    INDEX
    Explanations

    news-related terms and legal or court-related information

    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
    291
    +0.12
    0.5%
    113
    +0.11
    0.4%
    18
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.12
    0.09
    291
    +0.11
    0.11
    649
    +0.10
    0.04
    Negative Logits
    sed
    -0.86
     stocking
    -0.78
     footsteps
    -0.78
    ilater
    -0.75
    etime
    -0.74
     vocals
    -0.72
    avorite
    -0.72
    ilings
    -0.70
     lifes
    -0.69
    liam
    -0.69
    POSITIVE LOGITS
     Herald
    1.33
     Tribune
    1.32
     Newspaper
    1.21
     Newsp
    1.08
     Chronicle
    1.05
     Dispatch
    1.05
     Observer
    1.05
     newspaper
    1.05
    Journal
    1.02
     Editorial
    0.99
    Activations Density 6.216%

    No Known Activations