© 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. 13733
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    male names and related titles or identifiers

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    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%
    481
    +0.15
    0.6%
    664
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.25
    0.28
    232
    +0.15
    0.21
    145
    +0.13
    0.12
    Negative Logits
    CONCLUS
    -0.74
    versive
    -0.73
    tracking
    -0.71
     cybersecurity
    -0.70
     youtube
    -0.70
     dystopian
    -0.69
     predictive
    -0.68
     Competitive
    -0.68
     unprepared
    -0.67
     anecd
    -0.67
    POSITIVE LOGITS
     Haas
    0.92
     Sr
    0.91
     Jr
    0.87
    mie
    0.87
    ania
    0.85
     Marshall
    0.84
    iva
    0.81
     Emin
    0.81
     Gomez
    0.81
    abee
    0.80
    Activations Density 14.377%

    No Known Activations