© 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. 31702
    Prev
    Next
    INDEX
    Explanations

    information related to employment changes and political activities of individuals

    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
    +0.35
    1.7%
    393
    +0.23
    1.2%
    43
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.35
    0.18
    393
    +0.23
    0.27
    297
    +0.09
    0.13
    Negative Logits
    idepress
    -0.55
    othal
    -0.55
    omen
    -0.55
     receptors
    -0.54
    overs
    -0.54
     prompt
    -0.53
    FIX
    -0.53
    process
    -0.53
    strous
    -0.52
     correctness
    -0.52
    POSITIVE LOGITS
     Jr
    1.28
     Sr
    1.14
     aka
    0.99
    Jr
    0.88
     who
    0.81
     QC
    0.80
    who
    0.78
     whose
    0.78
     PhD
    0.75
     formerly
    0.73
    Activations Density 10.656%

    No Known Activations