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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11132
    Prev
    Next
    INDEX
    Explanations

    phrases related to departures or resignations

    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
    354
    +0.13
    0.6%
    216
    +0.12
    0.5%
    763
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.02
    354
    +0.12
    0.02
    24
    +0.11
    0.01
    Negative Logits
    ness
    -0.73
    ãĤī
    -0.71
    ITNESS
    -0.69
     edible
    -0.65
    earchers
    -0.64
    lyak
    -0.63
    OVER
    -0.63
    ances
    -0.63
    ĸļ
    -0.63
    printed
    -0.63
    POSITIVE LOGITS
    ially
    1.05
    SHIP
    1.03
    iola
    0.88
    ator
    0.88
    ios
    0.88
    ian
    0.87
    ators
    0.87
    hips
    0.87
    oldemort
    0.86
    io
    0.86
    Activations Density 0.056%

    No Known Activations