© 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
    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. 3667
    Prev
    Next
    INDEX
    Explanations

    a mix of different characters, possibly non-English characters or symbols

    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
    233
    +0.14
    0.6%
    406
    +0.13
    0.5%
    555
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.14
    0.12
    393
    +0.13
    0.16
    504
    +0.12
    0.06
    Negative Logits
     Dragonbound
    -0.98
    oulos
    -0.87
    aneers
    -0.79
    espie
    -0.77
     proximity
    -0.75
    itaire
    -0.74
    ACTED
    -0.73
    ettings
    -0.73
    isites
    -0.71
    theless
    -0.71
    POSITIVE LOGITS
    ´
    1.78
    ¤
    1.76
    Ķ
    1.71
    ľ
    1.70
    Į
    1.70
    ¹
    1.69
    ¸
    1.69
    Ħ
    1.68
    ĥ
    1.68
    °
    1.68
    Activations Density 6.163%

    No Known Activations