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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 4524
    Prev
    Next
    INDEX
    Explanations

    terms related to energy production and distribution, particularly focusing on the use of nuclear plants and electricity grid operations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    480
    +0.49
    2.5%
    481
    +0.12
    0.6%
    420
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.49
    0.18
    480
    +0.12
    0.00
    575
    +0.11
    0.14
    Negative Logits
    ãĥīãĥ©
    -0.61
    essor
    -0.54
    vae
    -0.53
    ãĥĻ
    -0.53
    å°Ĩ
    -0.52
    ?).
    -0.52
    ewitness
    -0.52
    ĪĴ
    -0.51
    ãĥ¯ãĥ³
    -0.49
    ãģĹ
    -0.49
    POSITIVE LOGITS
     whereas
    1.09
     because
    1.06
    ;
    0.97
     although
    0.95
     but
    0.95
    .
    0.84
     whilst
    0.80
     unless
    0.77
     insofar
    0.77
     while
    0.77
    Activations Density 3.098%

    No Known Activations