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. 23670
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "collaborative" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered 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
    554
    +0.13
    0.6%
    251
    +0.11
    0.5%
    483
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.13
    0.02
    554
    +0.11
    0.01
    483
    +0.10
    0.01
    Negative Logits
    fulness
    -0.73
    oshenko
    -0.71
    thing
    -0.67
    ¥µ
    -0.65
    visor
    -0.64
    chal
    -0.64
    BLE
    -0.63
    qua
    -0.63
    PDATE
    -0.61
    culosis
    -0.60
    POSITIVE LOGITS
    oqu
    1.12
    ateral
    1.10
    ocation
    1.09
    apsed
    1.09
    ision
    1.06
    apse
    1.04
    ocations
    1.03
    ider
    1.03
    ossus
    1.03
    iery
    0.99
    Activations Density 0.022%

    No Known Activations