© 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. 36005
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentions or plans

    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
    +0.23
    1.2%
    393
    +0.12
    0.6%
    471
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.23
    0.33
    640
    +0.12
    0.30
    608
    +0.09
    0.24
    Negative Logits
    roy
    -0.67
    worth
    -0.62
    workers
    -0.59
    shown
    -0.57
    mask
    -0.56
    imore
    -0.54
    eros
    -0.53
    ©¶æ¥µ
    -0.53
     custody
    -0.51
    Cub
    -0.50
    POSITIVE LOGITS
     emulate
    0.89
     improve
    0.74
     broaden
    0.73
     tighten
    0.72
     avoid
    0.72
     resume
    0.71
     incorporate
    0.70
     engage
    0.70
    asty
    0.69
     minimize
    0.69
    Activations Density 14.456%

    No Known Activations