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 24576
    5. 8-RES_FS24576-JB
    6. 11508
    Prev
    Next
    INDEX
    Explanations

    information related to hair and hair products or chemical compounds and their usage

    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
    480
    +0.49
    2.6%
    266
    +0.13
    0.7%
    420
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.49
    0.02
    266
    +0.13
    0.09
    351
    +0.11
    0.03
    Negative Logits
     advers
    -0.65
    ĪĴ
    -0.64
     scoreboard
    -0.63
    Security
    -0.61
     UNCLASSIFIED
    -0.60
     Eag
    -0.60
    Task
    -0.60
    Justice
    -0.60
     Inspector
    -0.60
    idable
    -0.59
    POSITIVE LOGITS
     herbal
    1.15
     edible
    1.14
     fermented
    1.14
     arom
    1.12
     dehyd
    1.12
     nutrients
    1.11
     foods
    1.10
     herbs
    1.10
     alk
    1.09
     aromatic
    1.08
    Activations Density 0.991%

    No Known Activations