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. 34436
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to businesses, organizations, and individuals

    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
    +0.25
    1.0%
    51
    +0.13
    0.5%
    475
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.25
    0.20
    548
    +0.13
    0.01
    475
    +0.13
    0.11
    Negative Logits
     simultane
    -0.86
    nesday
    -0.80
    arcity
    -0.80
     resil
    -0.80
    ortium
    -0.75
    leck
    -0.74
     CCP
    -0.71
    emporary
    -0.70
    wcs
    -0.69
    mercial
    -0.66
    POSITIVE LOGITS
    INAL
    0.84
    nih
    0.82
    ibrary
    0.79
    ICT
    0.78
    riage
    0.73
    roid
    0.72
     Extensions
    0.71
    kov
    0.69
    EH
    0.69
    agle
    0.69
    Activations Density 28.595%

    No Known Activations