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. 4550
    Prev
    Next
    INDEX
    Explanations

    words related to natural occurrences or resources, particularly focusing on natural gas and environmental impacts

    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
    438
    +0.11
    0.5%
    178
    +0.11
    0.5%
    276
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    535
    +0.11
    0.03
    284
    +0.11
    0.03
    438
    +0.10
    0.03
    Negative Logits
    ammy
    -0.70
    enance
    -0.70
     Parables
    -0.65
    lished
    -0.64
    Reloaded
    -0.64
    rology
    -0.64
    rav
    -0.63
    ATS
    -0.63
    raper
    -0.63
    raq
    -0.62
    POSITIVE LOGITS
    istic
    1.26
    ized
    1.13
    istically
    1.10
    ization
    1.09
    izations
    1.05
    izes
    1.02
    izable
    0.98
    ised
    0.98
    isation
    0.98
    izing
    0.97
    Activations Density 0.164%

    No Known Activations