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 3072
    5. 8-RES_FS3072-JB
    6. 2602
    Prev
    Next
    INDEX
    Explanations

    information about internet companies and events

    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
    31
    +0.10
    0.5%
    240
    +0.10
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.09
    314
    +0.10
    0.02
    128
    +0.09
    0.07
    Negative Logits
    ĪĴ
    -0.80
    NESS
    -0.80
    LEY
    -0.76
     resil
    -0.72
    å§«
    -0.72
    çĭ
    -0.67
     Mellon
    -0.67
    è£
    -0.66
    ħĭ
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
    POSITIVE LOGITS
    ounds
    0.97
    ou
    0.97
    angs
    0.97
    unny
    0.96
    ynamic
    0.96
    unk
    0.96
    ust
    0.96
    alt
    0.95
    orthern
    0.94
    umbled
    0.94
    Activations Density 0.615%

    No Known Activations