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 49152
    5. 8-RES_FS49152-JB
    6. 37075
    Prev
    Next
    INDEX
    Explanations

    terms related to molecular biology and biochemistry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    288
    +0.16
    0.7%
    578
    +0.14
    0.6%
    220
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.16
    0.01
    560
    +0.14
    0.01
    220
    +0.10
    0.01
    Negative Logits
    swick
    -0.89
    ħĭ
    -0.79
    ĪĴ
    -0.78
    UAL
    -0.76
    taboola
    -0.75
    Virgin
    -0.75
    é»Ĵ
    -0.74
    udeb
    -0.74
    emouth
    -0.72
    zzo
    -0.72
    POSITIVE LOGITS
     biology
    1.19
     biologist
    1.11
     biologists
    0.98
    ized
    0.98
     imaging
    0.93
     cloning
    0.93
     organisms
    0.92
    ities
    0.91
    ity
    0.91
     Biology
    0.91
    Activations Density 0.008%

    No Known Activations