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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4185
    Prev
    Next
    INDEX
    Explanations

    phrases related to soccer clubs, teams, and player transactions

    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
    1.0%
    326
    +0.14
    0.6%
    48
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.23
    -0.02
    578
    +0.14
    0.03
    294
    +0.12
    0.02
    Negative Logits
    mond
    -0.87
    lihood
    -0.86
    Downloadha
    -0.84
    ously
    -0.82
     Ples
    -0.80
     bart
    -0.77
     Alibaba
    -0.75
    ysis
    -0.74
    vier
    -0.73
    onym
    -0.70
    POSITIVE LOGITS
    FC
    0.88
    rica
    0.83
    ORE
    0.81
     Cincinnati
    0.81
    apo
    0.80
    RIC
    0.80
    ilage
    0.79
    soc
    0.79
    AT
    0.77
    KC
    0.77
    Activations Density 4.557%

    No Known Activations