© 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. 35889
    Prev
    Next
    INDEX
    Explanations

    websites and online platforms, especially those related to technology and community engagement

    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
    1.1%
    640
    +0.22
    1.0%
    679
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.41
    6
    +0.22
    0.34
    679
    +0.13
    0.33
    Negative Logits
     grounding
    -0.85
     overlooked
    -0.81
     parting
    -0.79
     shaving
    -0.79
     footing
    -0.78
     temperament
    -0.77
     leaving
    -0.76
     voting
    -0.75
     dispers
    -0.75
     sway
    -0.73
    POSITIVE LOGITS
    com
    1.53
    org
    1.40
    edu
    1.33
    Org
    1.27
    wordpress
    1.26
    net
    1.25
    fm
    1.23
    blogspot
    1.23
    gov
    1.19
    dll
    1.19
    Activations Density 12.913%

    No Known Activations