© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13878
    Prev
    Next
    INDEX
    Explanations

    words related to employment and personnel management

    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%
    393
    +0.19
    0.9%
    150
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.28
    0.28
    0
    +0.19
    0.14
    128
    +0.10
    0.14
    Negative Logits
    Senator
    -0.68
    Phys
    -0.68
    Sup
    -0.65
    Times
    -0.64
    otal
    -0.63
    BO
    -0.62
    Deal
    -0.62
    Dispatch
    -0.60
    Gaza
    -0.60
    :(
    -0.59
    POSITIVE LOGITS
    rogens
    0.92
     onwards
    0.89
     onward
    0.86
    rogen
    0.83
     preferably
    0.80
     then
    0.78
    romeda
    0.75
     thence
    0.74
     consequently
    0.72
     thus
    0.71
    Activations Density 10.378%

    No Known Activations