© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18949
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements or arrangements between individuals or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    665
    +0.15
    0.7%
    445
    +0.13
    0.6%
    654
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.15
    0.04
    654
    +0.13
    0.03
    445
    +0.10
    0.03
    Negative Logits
    ortunate
    -0.81
    ults
    -0.77
    icularly
    -0.73
    laughter
    -0.70
    ï¸ı
    -0.69
    hur
    -0.66
    lance
    -0.66
    clips
    -0.66
    mania
    -0.66
    grain
    -0.65
    POSITIVE LOGITS
     waive
    1.17
     cooperate
    1.10
     accept
    1.09
     participate
    1.08
     abide
    1.06
     donate
    1.03
     surrender
    1.01
     settle
    1.00
     negotiate
    0.99
     collaborate
    0.99
    Activations Density 0.069%

    No Known Activations