© 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. 7294
    Prev
    Next
    INDEX
    Explanations

    the word "dim" followed by a numerical value, particularly those indicating a level of medical condition or measurement

    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
    191
    +0.10
    0.4%
    441
    +0.10
    0.4%
    549
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.10
    0.01
    232
    +0.10
    0.01
    539
    +0.09
    0.01
    Negative Logits
    FactoryReloaded
    -0.80
    OUP
    -0.73
    REDACTED
    -0.70
    lli
    -0.68
    CRIP
    -0.66
    ALLY
    -0.66
    hips
    -0.66
    Untitled
    -0.63
    OAD
    -0.63
    AIN
    -0.62
    POSITIVE LOGITS
    inished
    1.46
    ming
    1.27
    ethy
    1.22
    ples
    1.20
    ensions
    1.19
    orph
    1.12
    mers
    1.09
    itri
    1.06
    ension
    1.03
    est
    1.00
    Activations Density 0.018%

    No Known Activations