© 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. 35017
    Prev
    Next
    INDEX
    Explanations

    sequences of hexadecimal characters

    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
    87
    +0.27
    1.3%
    64
    +0.12
    0.6%
    380
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.27
    0.07
    176
    +0.12
    0.04
    87
    +0.12
    -0.07
    Negative Logits
     Bulgar
    -0.69
     Balk
    -0.64
     gradient
    -0.63
    ioxide
    -0.60
     Olymp
    -0.59
    ãĥ¼ãĥĨ
    -0.59
    gradient
    -0.58
     centrif
    -0.58
     manif
    -0.58
    ç«
    -0.58
    POSITIVE LOGITS
    EStream
    0.75
    elsen
    0.69
    dinand
    0.67
    ongyang
    0.66
    imei
    0.66
    pees
    0.64
    oyal
    0.62
    OHN
    0.61
    christ
    0.59
    onest
    0.58
    Activations Density 3.086%

    No Known Activations