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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 40206
    Prev
    Next
    INDEX
    Explanations

    information related to awards ceremonies, movies, and notable individuals within the film industry

    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
    +0.33
    1.4%
    745
    +0.12
    0.5%
    408
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    644
    +0.33
    0.13
    480
    +0.12
    -0.16
    745
    +0.11
    -0.26
    Negative Logits
    luaj
    -0.92
    igenous
    -0.81
    cosystem
    -0.81
    utics
    -0.77
    thood
    -0.76
    ãĤ¤ãĥĪ
    -0.76
    fam
    -0.75
    ankind
    -0.74
    å¥
    -0.74
    é£
    -0.73
    POSITIVE LOGITS
     *)
    1.21
     typo
    1.03
     deleted
    0.92
     ONLY
    0.89
    !]
    0.89
     DID
    0.89
     ALWAYS
    0.87
     incorrectly
    0.86
    *)
    0.85
     spoilers
    0.83
    Activations Density 22.812%

    No Known Activations