© 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. 35779
    Prev
    Next
    INDEX
    Explanations

    mentions of geopolitical situations and conflicts, particularly related to war-torn countries and government actions

    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
    496
    +0.08
    0.5%
    550
    +0.08
    0.5%
    453
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.21
    658
    +0.08
    0.08
    365
    +0.07
    0.04
    Negative Logits
    assador
    -0.56
    azel
    -0.56
    */(
    -0.54
    ATURE
    -0.54
    tesy
    -0.53
    Service
    -0.53
    asso
    -0.52
    ATURES
    -0.52
    KN
    -0.52
    OST
    -0.51
    POSITIVE LOGITS
     regions
    0.89
     provinces
    0.89
     nations
    0.88
     industrialized
    0.87
     countries
    0.87
     counties
    0.86
     suburbs
    0.85
     sectors
    0.84
     towns
    0.79
     coastal
    0.78
    Activations Density 7.941%

    No Known Activations