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. 40233
    Prev
    Next
    INDEX
    Explanations

    details about art exhibitions and museum events

    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
    +0.23
    1.1%
    730
    +0.09
    0.4%
    198
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.23
    0.10
    487
    +0.09
    0.05
    765
    +0.08
    0.11
    Negative Logits
    yip
    -0.76
     throttle
    -0.69
     fastball
    -0.67
     shortened
    -0.67
     Lethal
    -0.66
     Kernel
    -0.64
    nir
    -0.63
     Lyft
    -0.63
    bleacher
    -0.61
     timeout
    -0.61
    POSITIVE LOGITS
     collections
    1.11
     exhibition
    1.07
     exhibitions
    1.06
     artwork
    1.04
     paintings
    1.02
     Collections
    1.01
     museum
    0.97
     curator
    0.97
     museums
    0.95
     exhibits
    0.94
    Activations Density 21.955%

    No Known Activations