© 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. 35415
    Prev
    Next
    INDEX
    Explanations

    locations and entities related to conflicts in the Middle East, specifically focusing on Syria and Iraq

    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
    +0.28
    1.3%
    57
    +0.12
    0.5%
    160
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    662
    +0.28
    0.11
    685
    +0.12
    0.01
    57
    +0.11
    0.06
    Negative Logits
    inarily
    -0.82
    owler
    -0.79
     Hawaiian
    -0.78
    arious
    -0.75
    print
    -0.73
    semb
    -0.72
    rotein
    -0.71
    tops
    -0.71
    OTE
    -0.70
    ramer
    -0.70
    POSITIVE LOGITS
    ascus
    0.82
     ravaged
    0.76
     Assad
    0.75
     flared
    0.72
    Assad
    0.72
     invaded
    0.71
     dispers
    0.71
     annexed
    0.69
    raq
    0.68
     Bashar
    0.68
    Activations Density 6.881%

    No Known Activations