© 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. 31848
    Prev
    Next
    INDEX
    Explanations

    mentions of specific extremist groups and political conflicts in the context of Africa

    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
    267
    +0.11
    0.6%
    541
    +0.10
    0.5%
    5
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.22
    709
    +0.10
    0.13
    288
    +0.09
    0.21
    Negative Logits
    ingham
    -0.79
    ++++++++++++++++
    -0.70
    mble
    -0.69
     McDonnell
    -0.67
    ablishment
    -0.63
     Pavilion
    -0.61
     Yosemite
    -0.58
     apr
    -0.57
    edom
    -0.56
    ership
    -0.56
    POSITIVE LOGITS
     Haram
    1.22
     Nigeria
    0.81
    vernment
    0.78
     Niger
    0.72
     Nigerian
    0.72
    rahim
    0.71
    otle
    0.68
    ongo
    0.68
     Boko
    0.67
    lia
    0.65
    Activations Density 7.743%

    No Known Activations