© 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. 36765
    Prev
    Next
    INDEX
    Explanations

    terms related to maritime activities and locations

    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
    +0.27
    1.2%
    459
    +0.12
    0.6%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.27
    0.09
    288
    +0.12
    0.24
    326
    +0.12
    0.26
    Negative Logits
    heimer
    -0.82
    izophren
    -0.75
    âĶģ
    -0.75
     Parenthood
    -0.73
    stract
    -0.73
    Bron
    -0.72
    tained
    -0.70
    Gene
    -0.69
    haar
    -0.69
    blance
    -0.67
    POSITIVE LOGITS
     sailing
    1.17
     sailed
    1.09
     HMS
    1.08
     vessels
    1.08
     sailor
    1.08
     fleet
    1.07
     ships
    1.07
     ship
    1.07
     boats
    1.04
    fleet
    1.03
    Activations Density 13.350%

    No Known Activations