© 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. 35043
    Prev
    Next
    INDEX
    Explanations

    references to physical activity and locations

    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
    523
    +0.08
    0.4%
    750
    +0.08
    0.4%
    181
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.08
    -0.12
    70
    +0.08
    0.10
    406
    +0.08
    0.09
    Negative Logits
    è¦ļéĨĴ
    -0.63
    lished
    -0.59
    ORTS
    -0.57
    ItemTracker
    -0.57
    è»
    -0.56
    Rated
    -0.54
    ij士
    -0.53
     Mayer
    -0.53
    æĸ¹
    -0.52
     AMERICA
    -0.51
    POSITIVE LOGITS
    tering
    0.80
    ter
    0.76
    ting
    0.68
    ving
    0.65
    wyn
    0.64
    oad
    0.64
    ounge
    0.64
    tered
    0.64
    ong
    0.63
    oaded
    0.63
    Activations Density 4.833%

    No Known Activations