© 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. 35807
    Prev
    Next
    INDEX
    Explanations

    mentions of seeking or searching

    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
    447
    +0.15
    0.7%
    581
    +0.12
    0.6%
    71
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    191
    +0.15
    0.04
    133
    +0.12
    0.07
    261
    +0.10
    0.05
    Negative Logits
     Democr
    -0.67
    Ö¼
    -0.64
     Notting
    -0.62
     rattled
    -0.61
     PowerPoint
    -0.60
     Typhoon
    -0.60
     shaken
    -0.58
    forced
    -0.58
     Bearing
    -0.57
     Cycle
    -0.57
    POSITIVE LOGITS
    ById
    0.99
     elusive
    0.97
     revenge
    0.82
     answers
    0.79
     inspiration
    0.77
     refuge
    0.71
     immortality
    0.70
    leground
    0.68
     effic
    0.67
     perfection
    0.64
    Activations Density 12.451%

    No Known Activations