© 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. 13836
    Prev
    Next
    INDEX
    Explanations

    phrases related to dominos or causality

    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
    +0.10
    0.6%
    71
    +0.10
    0.6%
    603
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    210
    +0.10
    0.05
    234
    +0.10
    0.09
    603
    +0.07
    0.07
    Negative Logits
    duino
    -0.61
    Downloadha
    -0.53
    velength
    -0.52
    ickr
    -0.51
    enegger
    -0.50
    icago
    -0.49
     CTR
    -0.47
    lance
    -0.47
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.46
    ulton
    -0.45
    POSITIVE LOGITS
    ese
    0.57
    omics
    0.57
    piece
    0.53
    ciating
    0.52
    ICAN
    0.51
    »Ĵ
    0.51
    icky
    0.51
    ij士
    0.50
    alian
    0.50
    amara
    0.50
    Activations Density 8.058%

    No Known Activations