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. 34411
    Prev
    Next
    INDEX
    Explanations

    temperature-related measurements and units

    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
    524
    +0.12
    0.5%
    616
    +0.12
    0.5%
    537
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.12
    0.10
    141
    +0.12
    0.08
    166
    +0.11
    0.08
    Negative Logits
    ulhu
    -0.82
    ****************
    -0.81
    UNCH
    -0.77
     Dodd
    -0.72
     planted
    -0.72
    ************
    -0.69
    amia
    -0.69
    ********************************
    -0.68
     Reply
    -0.68
    ppelin
    -0.67
    POSITIVE LOGITS
    rating
    0.97
    rated
    0.92
    ĩ
    0.83
    âĪĴ
    0.83
    iosity
    0.81
    fen
    0.80
    bid
    0.79
    ration
    0.79
    facing
    0.79
    mentation
    0.76
    Activations Density 3.729%

    No Known Activations