© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 35155
    Prev
    Next
    INDEX
    Explanations

    technical information about specific products or equipment

    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
    +0.11
    0.9%
    566
    +0.07
    0.6%
    393
    +0.07
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.19
    55
    +0.07
    0.20
    393
    +0.07
    0.26
    Negative Logits
    arms
    -0.37
    mare
    -0.37
    violence
    -0.37
    erity
    -0.37
     Millions
    -0.36
    Things
    -0.35
    angering
    -0.35
    steps
    -0.34
    arming
    -0.34
    paralle
    -0.34
    POSITIVE LOGITS
     reviewed
    0.54
     discontinued
    0.53
     awarded
    0.53
     replaced
    0.52
     initialized
    0.51
     evaluated
    0.51
     investigated
    0.51
     obtained
    0.51
     shown
    0.51
     able
    0.49
    Activations Density 11.535%

    No Known Activations