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 49152
    5. 8-RES_FS49152-JB
    6. 26061
    Prev
    Next
    INDEX
    Explanations

    themes related to justice and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.38
    1.9%
    330
    +0.10
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.38
    0.00
    567
    +0.10
    0.04
    642
    +0.10
    0.03
    Negative Logits
    çīĪ
    -0.74
     confir
    -0.61
    »Ĵ
    -0.60
    adel
    -0.58
    liga
    -0.55
    idav
    -0.55
    ij士
    -0.55
    iple
    -0.54
    mentioned
    -0.54
    ilde
    -0.54
    POSITIVE LOGITS
     unfairly
    0.82
     rapists
    0.74
     biologically
    0.71
     environmentally
    0.68
     "â̦
    0.67
     pedoph
    0.65
     terrorists
    0.65
     "
    0.64
     "'
    0.64
     psychologically
    0.64
    Activations Density 0.680%

    No Known Activations