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. 1321
    Prev
    Next
    INDEX
    Explanations

    references to technical or professional communication, such as emails and instructions

    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
    314
    +0.16
    0.7%
    160
    +0.15
    0.7%
    385
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.16
    0.08
    112
    +0.15
    0.06
    314
    +0.10
    0.02
    Negative Logits
     redu
    -0.70
    wagen
    -0.68
     piping
    -0.67
     ratios
    -0.67
     halfway
    -0.67
     seams
    -0.66
     factories
    -0.66
     reckoning
    -0.65
     rooft
    -0.65
     regression
    -0.65
    POSITIVE LOGITS
    ?]
    1.68
    !]
    1.54
    sic
    1.50
    REDACTED
    1.40
    â̦]
    1.36
     edit
    1.34
    ...]
    1.32
    email
    1.29
    ](
    1.28
    actionDate
    1.24
    Activations Density 0.384%

    No Known Activations