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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36420
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and events, specifically related to the Middle East and South Asia

    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
    320
    +0.03
    0.6%
    373
    +0.03
    0.5%
    175
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.03
    -0.13
    406
    +0.03
    0.10
    639
    +0.03
    0.10
    Negative Logits
    nect
    -0.21
    gage
    -0.19
    wagon
    -0.19
    itol
    -0.18
    iture
    -0.18
    crew
    -0.18
     Decay
    -0.18
    £ı
    -0.17
    aceutical
    -0.17
    ĪĴ
    -0.17
    POSITIVE LOGITS
    istan
    0.20
     Abbas
    0.19
     Mush
    0.19
     Islam
    0.18
    ania
    0.18
     Sak
    0.17
     Hassan
    0.17
     Alam
    0.17
     Yus
    0.17
     Ahmed
    0.17
    Activations Density 5.679%

    No Known Activations