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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 34596
    Prev
    Next
    INDEX
    Explanations

    frequent mentions of the term "Hill"

    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
    +0.24
    1.1%
    99
    +0.19
    0.8%
    659
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.24
    0.09
    325
    +0.19
    0.09
    99
    +0.15
    0.09
    Negative Logits
    uality
    -0.73
     Alonso
    -0.73
    glomer
    -0.73
    ULAR
    -0.72
     Norn
    -0.72
    ============
    -0.71
    âĹ¼
    -0.71
     oppos
    -0.70
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.70
    lihood
    -0.70
    POSITIVE LOGITS
    iard
    1.36
    top
    1.09
    yer
    1.07
    side
    1.03
    tops
    0.99
    bill
    0.98
    castle
    0.96
    marks
    0.91
    hog
    0.91
    sburgh
    0.87
    Activations Density 5.967%

    No Known Activations