© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 36422
    Prev
    Next
    INDEX
    Explanations

    symbols or symbolic representations

    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
    +0.24
    1.3%
    210
    +0.11
    0.6%
    362
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    528
    +0.24
    0.09
    210
    +0.11
    0.07
    393
    +0.10
    0.23
    Negative Logits
    scrib
    -0.54
     consulted
    -0.54
    neau
    -0.53
    zon
    -0.53
    iaries
    -0.53
    ahn
    -0.52
    published
    -0.52
    quartered
    -0.51
    elle
    -0.50
    soon
    -0.50
    POSITIVE LOGITS
     eternity
    0.63
     bravery
    0.61
     masculinity
    0.61
     Mata
    0.60
     virtues
    0.60
     sentiments
    0.59
    America
    0.59
    rium
    0.59
     Revival
    0.59
     disrespect
    0.58
    Activations Density 9.229%

    No Known Activations