© 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. 36022
    Prev
    Next
    INDEX
    Explanations

    information related to technology events or updates, potentially focusing on financial aspects, conferences, and specific speakers

    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
    1.3%
    314
    +0.09
    0.5%
    630
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.34
    283
    +0.09
    0.01
    375
    +0.09
    0.06
    Negative Logits
    axy
    -0.63
    lihood
    -0.54
    itiveness
    -0.53
     concedes
    -0.53
    atis
    -0.51
     pun
    -0.50
    them
    -0.49
    aqu
    -0.49
     heavens
    -0.48
    Sov
    -0.48
    POSITIVE LOGITS
    owler
    0.58
    FINE
    0.55
    assies
    0.55
    ornia
    0.54
    auga
    0.53
    Ô
    0.53
    ukong
    0.52
    htaking
    0.52
     Thomson
    0.52
    isine
    0.52
    Activations Density 19.075%

    No Known Activations