© 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. 9448
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to technological advancements or agency-related terms

    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
    317
    +0.11
    0.5%
    683
    +0.09
    0.4%
    391
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    687
    +0.11
    0.03
    317
    +0.09
    0.03
    455
    +0.09
    0.03
    Negative Logits
     outp
    -0.80
    owered
    -0.71
    mouth
    -0.67
     paraly
    -0.61
     idol
    -0.60
    program
    -0.59
     prank
    -0.58
     paralyzed
    -0.57
    6000
    -0.57
     [+
    -0.57
    POSITIVE LOGITS
     detail
    1.01
     later
    0.99
     hereafter
    0.92
    ipedia
    0.90
    }}}
    0.90
     details
    0.85
     below
    0.80
    later
    0.80
    fter
    0.76
     summar
    0.75
    Activations Density 0.149%

    No Known Activations