© 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. 14157
    Prev
    Next
    INDEX
    Explanations

    technical details about satellite launches and climate data

    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
    155
    +0.12
    0.5%
    176
    +0.12
    0.5%
    506
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.12
    0.13
    101
    +0.12
    0.24
    393
    +0.11
    0.27
    Negative Logits
    ĸļ
    -1.07
    emale
    -0.97
    vier
    -0.89
    erd
    -0.85
    ĨĴ
    -0.81
    aughs
    -0.80
    abet
    -0.80
    oday
    -0.78
    deen
    -0.77
    ocrates
    -0.77
    POSITIVE LOGITS
    .''.
    0.63
     mainland
    0.63
     abnorm
    0.62
     behalf
    0.62
     cancell
    0.60
     TC
    0.59
     either
    0.58
    .'"
    0.58
    '.
    0.56
     abnormalities
    0.56
    Activations Density 13.034%

    No Known Activations