© 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 3072
    9. 8-RES_FS3072-JB
    11. 2973
    Prev
    Next
    INDEX
    Explanations

    political and legal news related to investigations and military 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_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    640
    +0.28
    1.3%
    649
    +0.12
    0.6%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.24
    94
    +0.12
    0.19
    539
    +0.10
    0.14
    Negative Logits
    lections
    -0.67
    minist
    -0.65
    boro
    -0.64
     endeav
    -0.62
    utical
    -0.61
     endeavour
    -0.59
    heit
    -0.58
    tons
    -0.56
     everyday
    -0.56
     util
    -0.56
    POSITIVE LOGITS
    PHOTOS
    0.94
    Scroll
    0.89
    Asked
    0.89
     Related
    0.84
    Newsletter
    0.82
    Bus
    0.81
    However
    0.80
    Write
    0.77
    Reporting
    0.76
    Meanwhile
    0.76
    Activations Density 0.996%

    No Known Activations