© 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. 3864
    Prev
    Next
    INDEX
    Explanations

    substrings or words related to acronyms and names of companies or organizations

    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
    376
    +0.14
    0.7%
    447
    +0.13
    0.6%
    187
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.09
    187
    +0.13
    0.09
    57
    +0.13
    0.07
    Negative Logits
     tipped
    -0.67
     Guinness
    -0.66
     Eleven
    -0.64
    ãĤ¡
    -0.63
     tips
    -0.62
     Hath
    -0.60
     cider
    -0.60
     centre
    -0.59
     Nep
    -0.59
     tip
    -0.59
    POSITIVE LOGITS
    useum
    1.15
    umbai
    1.13
    asonic
    1.04
    ISSION
    1.04
    asonry
    1.03
    OST
    1.03
    uzzle
    1.01
    ARK
    1.01
    ixed
    1.01
    otive
    0.99
    Activations Density 3.854%

    No Known Activations