© 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. 35761
    Prev
    Next
    INDEX
    Explanations

    historical events and military-related terms

    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
    +0.09
    0.7%
    459
    +0.07
    0.6%
    420
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.09
    0.28
    301
    +0.07
    0.11
    6
    +0.06
    0.16
    Negative Logits
    rouse
    -0.45
     Parsons
    -0.40
    ebus
    -0.40
    yip
    -0.38
     Rhythm
    -0.38
    Bloom
    -0.38
    ickr
    -0.37
    igne
    -0.35
     Tone
    -0.35
    iesta
    -0.35
    POSITIVE LOGITS
    ment
    0.60
    statement
    0.47
     proceedings
    0.45
    atorium
    0.45
    dated
    0.45
    ments
    0.42
    rarily
    0.42
     relic
    0.41
    ations
    0.40
    ably
    0.40
    Activations Density 14.277%

    No Known Activations