Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4171
    Prev
    Next
    INDEX
    Explanations

    words related to wind energy and wind power

    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
    251
    +0.14
    0.5%
    718
    +0.13
    0.5%
    755
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    272
    +0.14
    0.07
    251
    +0.13
    0.06
    538
    +0.13
    0.05
    Negative Logits
    Ô
    -0.90
    usalem
    -0.86
    henko
    -0.85
    issy
    -0.83
    ucha
    -0.82
    onse
    -0.81
    utical
    -0.80
    arij
    -0.79
    tein
    -0.79
    endants
    -0.77
    POSITIVE LOGITS
     turbines
    1.25
     turbine
    1.21
    mill
    1.21
    shield
    1.19
    blown
    1.13
     gust
    1.05
    storms
    0.99
    lass
    0.97
     blowing
    0.97
    wind
    0.92
    Activations Density 5.305%

    No Known Activations