Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45482
    Prev
    Next
    INDEX
    Explanations

    significant terms related to geology and geological exploration

    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
    235
    +0.13
    0.8%
    649
    +0.08
    0.5%
    707
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    649
    +0.13
    0.02
    235
    +0.08
    0.10
    450
    +0.08
    0.07
    Negative Logits
    lessly
    -0.78
    nea
    -0.70
    kus
    -0.64
    nered
    -0.60
    edly
    -0.58
    epad
    -0.56
    ĪĴ
    -0.54
    edited
    -0.53
    lyak
    -0.52
    ned
    -0.52
    POSITIVE LOGITS
     expedition
    0.69
     geological
    0.68
     Geological
    0.68
     Survey
    0.64
     Warfare
    0.63
     distress
    0.62
     excav
    0.62
     monuments
    0.61
     Instruments
    0.61
     landmarks
    0.60
    Activations Density 8.595%

    No Known Activations