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. 34465
    Prev
    Next
    INDEX
    Explanations

    terms related to sports commentary, player performance evaluations, and personal anecdotes

    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
    651
    +0.09
    0.5%
    393
    +0.08
    0.4%
    542
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.09
    0.17
    689
    +0.08
    0.12
    202
    +0.08
    0.10
    Negative Logits
    ãĥ´ãĤ¡
    -0.60
    lav
    -0.57
    ²
    -0.55
    hips
    -0.53
    ãĥł
    -0.52
    ãĥ©
    -0.52
    conduct
    -0.51
    VA
    -0.51
    ãĤ±
    -0.50
    currently
    -0.49
    POSITIVE LOGITS
    chy
    1.01
    alian
    0.85
    atic
    0.70
    self
    0.65
    icult
    0.62
    atically
    0.61
    iner
    0.61
    unes
    0.59
    crop
    0.58
    ueller
    0.58
    Activations Density 6.024%

    No Known Activations