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. 11243
    Prev
    Next
    INDEX
    Explanations

    cities or locations around the world

    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
    263
    +0.11
    0.5%
    45
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.11
    0.05
    693
    +0.11
    0.05
    430
    +0.10
    0.05
    Negative Logits
    achu
    -0.85
    aeus
    -0.84
    andise
    -0.76
    eton
    -0.71
    rd
    -0.70
    rous
    -0.68
    ulic
    -0.67
    ocratic
    -0.65
    ãĤ©
    -0.65
    reek
    -0.65
    POSITIVE LOGITS
    20439
    0.93
    teen
    0.76
    worthiness
    0.76
    384
    0.72
    teenth
    0.69
    nd
    0.68
    bat
    0.66
    6666
    0.65
    mia
    0.64
    tenance
    0.63
    Activations Density 0.103%

    No Known Activations