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. 34503
    Prev
    Next
    INDEX
    Explanations

    references to organizations related to trade and health

    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
    525
    +0.09
    0.5%
    127
    +0.08
    0.4%
    129
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.09
    0.07
    116
    +0.08
    0.06
    373
    +0.07
    -0.18
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.64
    Downloadha
    -0.62
    é»Ĵ
    -0.59
    ibly
    -0.59
    cham
    -0.59
    anco
    -0.54
    20439
    -0.53
    worldly
    -0.52
    Reviewer
    -0.52
    uckland
    -0.52
    POSITIVE LOGITS
     Organization
    0.66
     Fund
    0.65
     Institute
    0.63
     Organisation
    0.62
     Facility
    0.60
     Forum
    0.59
     Center
    0.59
     Toll
    0.58
     Prize
    0.58
     Group
    0.57
    Activations Density 8.236%

    No Known Activations