© 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 EvalsExportsinterp-engineNEWAPI 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. 31502
    Prev
    Next
    INDEX
    Explanations

    words related to news articles and current events

    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
    226
    +0.16
    0.6%
    360
    +0.14
    0.5%
    151
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.16
    0.18
    447
    +0.14
    0.20
    64
    +0.12
    -0.17
    Negative Logits
    eff
    -0.91
    rarily
    -0.87
    orate
    -0.79
    eways
    -0.78
    antics
    -0.77
    ves
    -0.77
    velt
    -0.75
    iggurat
    -0.75
    iotic
    -0.75
    arter
    -0.74
    POSITIVE LOGITS
     known
    1.13
     nicknamed
    1.06
     spelled
    1.01
     renamed
    1.00
     dubbed
    1.00
     Called
    0.94
     comprising
    0.93
     referred
    0.93
     Known
    0.92
     TBA
    0.91
    Activations Density 7.103%

    No Known Activations