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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 4556
    Prev
    Next
    INDEX
    Explanations

    phrases related to political affairs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.34
    1.3%
    679
    +0.17
    0.6%
    485
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.34
    0.12
    146
    +0.17
    0.07
    575
    +0.12
    0.08
    Negative Logits
    gling
    -1.03
    own
    -0.97
    astic
    -0.97
    abase
    -0.96
    xious
    -0.95
    ough
    -0.95
    ones
    -0.93
    ning
    -0.93
    sum
    -0.93
    iple
    -0.92
    POSITIVE LOGITS
    pring
    1.23
    afety
    1.08
    chool
    1.04
    hips
    1.01
     Correspond
    0.98
     affairs
    0.96
    hip
    0.94
     Profession
    0.94
    mith
    0.93
    pace
    0.91
    Activations Density 1.048%

    No Known Activations