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. 45103
    Prev
    Next
    INDEX
    Explanations

    sentences related to social issues and politics

    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
    +0.25
    1.1%
    326
    +0.13
    0.6%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    536
    +0.25
    0.11
    661
    +0.13
    0.10
    237
    +0.11
    0.10
    Negative Logits
     coff
    -0.59
     itiner
    -0.58
     Spani
    -0.58
     pots
    -0.58
     precinct
    -0.57
     schedules
    -0.55
     resent
    -0.55
     Britons
    -0.55
     crus
    -0.54
     Pharaoh
    -0.54
    POSITIVE LOGITS
    ELF
    0.86
    wered
    0.83
    lightly
    0.83
    ustainable
    0.81
    aurus
    0.80
    mean
    0.76
     gonna
    0.75
    uddenly
    0.74
    ought
    0.74
    nown
    0.73
    Activations Density 8.073%

    No Known Activations