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. 45120
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures, policy decisions, and controversial social issues

    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
    1.0%
    71
    +0.12
    0.5%
    512
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.25
    0.06
    520
    +0.12
    0.07
    460
    +0.11
    0.06
    Negative Logits
    erd
    -0.86
    rouse
    -0.75
    iry
    -0.73
    idas
    -0.73
    mented
    -0.71
    alez
    -0.65
    Fram
    -0.64
    aukee
    -0.64
    ories
    -0.64
    insula
    -0.64
    POSITIVE LOGITS
    NULL
    0.83
    nit
    0.83
    س
    0.70
    ña
    0.69
    minus
    0.68
    forth
    0.67
    BuyableInstoreAndOnline
    0.67
     assume
    0.66
     assumes
    0.66
    uracy
    0.66
    Activations Density 5.911%

    No Known Activations