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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 34282
    Prev
    Next
    INDEX
    Explanations

    mentions of political events and discussions

    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
    +0.19
    1.1%
    640
    +0.12
    0.7%
    393
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.19
    0.20
    123
    +0.12
    0.16
    22
    +0.11
    0.17
    Negative Logits
    âĿ
    -0.59
    ļ
    -0.56
    soever
    -0.55
    ¿½
    -0.54
    tre
    -0.52
     inherit
    -0.52
     citiz
    -0.51
    ĺħ
    -0.50
    izens
    -0.50
     ingred
    -0.49
    POSITIVE LOGITS
     conjunction
    0.98
     lieu
    0.95
     favor
    0.87
     accordance
    0.86
     vitro
    0.83
     regards
    0.78
     order
    0.77
     favour
    0.76
     advance
    0.74
    clusively
    0.73
    Activations Density 8.617%

    No Known Activations