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. 45506
    Prev
    Next
    INDEX
    Explanations

    phrases related to political activities and decision-making

    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
    +0.31
    1.6%
    481
    +0.21
    1.1%
    393
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.31
    0.41
    393
    +0.21
    0.42
    283
    +0.15
    0.04
    Negative Logits
    ulf
    -0.62
    ¹
    -0.59
    Sov
    -0.59
    ago
    -0.59
    piration
    -0.58
    isi
    -0.57
    ²
    -0.56
    в
    -0.56
    »
    -0.56
    ong
    -0.56
    POSITIVE LOGITS
     lookout
    0.67
     DISTRICT
    0.65
     flanked
    0.60
     ready
    0.58
     benches
    0.56
     surrounded
    0.56
    INGTON
    0.56
    orld
    0.54
     nowhere
    0.53
    along
    0.52
    Activations Density 21.075%

    No Known Activations