© 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. 40446
    Prev
    Next
    INDEX
    Explanations

    words related to physical work or physical acts, particularly those involving strength or effort

    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
    +0.13
    0.5%
    128
    +0.13
    0.5%
    326
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.14
    156
    +0.13
    0.05
    523
    +0.12
    0.06
    Negative Logits
    ICLE
    -0.91
    IFIC
    -0.85
    enegger
    -0.84
    ãģ®éŃĶ
    -0.81
    NEY
    -0.80
    bell
    -0.79
    ãĥ¥
    -0.78
    tainment
    -0.78
    terms
    -0.76
    ãĥ£
    -0.76
    POSITIVE LOGITS
    udge
    1.36
    asher
    1.34
    anted
    1.34
    ugg
    1.31
    ashes
    1.30
    ips
    1.29
    icker
    1.28
    ither
    1.28
    inging
    1.28
    ipper
    1.28
    Activations Density 4.709%

    No Known Activations