© 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. 33777
    Prev
    Next
    INDEX
    Explanations

    references to space exploration, specifically mentioning the moon

    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
    240
    +0.10
    0.5%
    178
    +0.09
    0.5%
    332
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.20
    288
    +0.09
    0.21
    48
    +0.08
    0.10
    Negative Logits
    ages
    -0.70
    er
    -0.64
    iral
    -0.62
    Rat
    -0.62
    hin
    -0.61
    isSpecialOrderable
    -0.60
    boro
    -0.60
    ername
    -0.59
    maker
    -0.59
    holes
    -0.59
    POSITIVE LOGITS
     eclipse
    0.82
     lunar
    0.69
    İĭ
    0.68
    cling
    0.65
    gments
    0.64
     Eclipse
    0.64
    conservancy
    0.63
     Lunar
    0.61
     simul
    0.60
    ãĥĪ
    0.60
    Activations Density 5.769%

    No Known Activations