© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13710
    Prev
    Next
    INDEX
    Explanations

    words related to sports and predictions

    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
    +0.22
    1.1%
    538
    +0.11
    0.5%
    656
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.22
    0.33
    370
    +0.11
    0.10
    608
    +0.10
    0.21
    Negative Logits
    ĸļ
    -0.77
    isons
    -0.68
    ELF
    -0.67
    velength
    -0.66
    yrics
    -0.66
    zanne
    -0.65
    ãĤ´
    -0.62
    ategory
    -0.62
    xtap
    -0.61
    iece
    -0.61
    POSITIVE LOGITS
     future
    0.85
     doom
    0.77
     rebound
    0.76
     sunset
    0.75
     CPC
    0.72
     2020
    0.72
     2019
    0.72
     TBD
    0.72
     Future
    0.69
     prospects
    0.69
    Activations Density 16.596%

    No Known Activations