© 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. 35087
    Prev
    Next
    INDEX
    Explanations

    phrases related to design and creativity

    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
    447
    +0.33
    1.6%
    640
    +0.10
    0.5%
    696
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.33
    0.39
    739
    +0.10
    0.07
    119
    +0.08
    0.17
    Negative Logits
    "},"
    -0.71
    Catalog
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.60
    rouse
    -0.59
    rive
    -0.58
     catalogue
    -0.57
    aughtered
    -0.57
    umerable
    -0.56
    qual
    -0.55
     Surrey
    -0.55
    POSITIVE LOGITS
     Lastly
    0.84
     disclaimer
    0.82
     note
    0.76
     parting
    0.73
    Lastly
    0.72
     aside
    0.71
     icing
    0.71
     kicker
    0.70
     FY
    0.69
    Disclaimer
    0.69
    Activations Density 24.202%

    No Known Activations