© 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. 34932
    Prev
    Next
    INDEX
    Explanations

    professional athletes' names and ranks

    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
    +0.26
    1.4%
    481
    +0.19
    1.0%
    286
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.26
    0.24
    640
    +0.19
    0.21
    176
    +0.10
    0.07
    Negative Logits
    ãĤ¤ãĥĪ
    -0.67
    vertisement
    -0.62
     {\
    -0.59
    conservancy
    -0.56
    ãĥ¼ãĤ¯
    -0.55
    noticed
    -0.54
    :/
    -0.54
    plin
    -0.54
    âĸĪâĸĪ
    -0.53
    issance
    -0.53
    POSITIVE LOGITS
     Others
    0.70
     Tel
    0.67
     Widow
    0.67
     TBA
    0.65
     Ibid
    0.65
     SOS
    0.64
     TOTAL
    0.63
     Sasha
    0.63
     Dia
    0.63
     Suc
    0.62
    Activations Density 8.977%

    No Known Activations