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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11336
    Prev
    Next
    INDEX
    Explanations

    information related to government surveillance and political disputes

    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
    +0.47
    2.3%
    567
    +0.11
    0.5%
    266
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.47
    0.01
    266
    +0.11
    0.09
    567
    +0.10
    0.05
    Negative Logits
    çīĪ
    -0.79
    »Ĵ
    -0.62
    cellaneous
    -0.60
    idav
    -0.60
    swick
    -0.58
    adel
    -0.56
     flurry
    -0.56
    urry
    -0.55
     alerts
    -0.55
    ILS
    -0.55
    POSITIVE LOGITS
     unconstitutional
    0.69
     morally
    0.68
     unfairly
    0.68
     pedoph
    0.68
    constitutional
    0.68
    "))
    0.67
     raping
    0.66
     vagina
    0.65
    acea
    0.65
    Jews
    0.63
    Activations Density 1.103%

    No Known Activations