Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 1307
    Prev
    Next
    INDEX
    Explanations

    countries and regions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    373
    +0.10
    0.5%
    570
    +0.09
    0.5%
    459
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.14
    176
    +0.09
    0.07
    232
    +0.09
    0.12
    Negative Logits
    imilar
    -0.65
    Reviewer
    -0.59
     WARN
    -0.58
    orically
    -0.55
    scrib
    -0.53
    esides
    -0.52
    minist
    -0.52
    staking
    -0.51
    ensional
    -0.51
    ewitness
    -0.50
    POSITIVE LOGITS
     TBA
    0.81
     etc
    0.74
     Extras
    0.69
     Jr
    0.64
     (+
    0.63
    ))))
    0.61
    ĸļ
    0.61
    rador
    0.61
    ĪĴ
    0.60
    cellaneous
    0.60
    Activations Density 4.670%

    No Known Activations