© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 45837
    Prev
    Next
    INDEX
    Explanations

    names and references related to political figures

    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
    659
    +0.12
    0.6%
    376
    +0.11
    0.5%
    103
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.09
    103
    +0.11
    0.08
    709
    +0.11
    0.09
    Negative Logits
    DragonMagazine
    -0.89
    istically
    -0.74
    culosis
    -0.72
    istical
    -0.72
    ical
    -0.71
     Nanto
    -0.69
    istics
    -0.68
    Interstitial
    -0.67
    stration
    -0.66
     Uriel
    -0.65
    POSITIVE LOGITS
    urdy
    1.00
    ourt
    0.96
    onduct
    0.94
    urry
    0.88
    apers
    0.87
    ott
    0.86
    aleb
    0.85
    ork
    0.85
    atcher
    0.82
    oll
    0.82
    Activations Density 5.388%

    No Known Activations