© 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. 32506
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic transactions and resource extraction

    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
    185
    +0.11
    0.5%
    402
    +0.10
    0.5%
    465
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.11
    0.09
    614
    +0.10
    0.04
    355
    +0.09
    0.07
    Negative Logits
     Democr
    -0.85
    house
    -0.78
    ãĥ³ãĤ¸
    -0.71
    houses
    -0.70
     hazards
    -0.64
    cers
    -0.63
    vironments
    -0.62
     halls
    -0.61
     Schwarzenegger
    -0.61
     martial
    -0.59
    POSITIVE LOGITS
    hemy
    1.15
    asp
    1.01
    heric
    0.88
    olitan
    0.87
    hemer
    0.86
    bian
    0.85
    inator
    0.84
    berries
    0.83
    oons
    0.82
    amily
    0.79
    Activations Density 7.705%

    No Known Activations