© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 10791
    Prev
    Next
    INDEX
    Explanations

    mentions of collaborative projects or collaborations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    +0.12
    0.6%
    483
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.13
    0.02
    554
    +0.12
    0.01
    483
    +0.10
    0.02
    Negative Logits
    fulness
    -0.74
    chal
    -0.70
    oshenko
    -0.70
    ¥µ
    -0.70
    thing
    -0.66
    culosis
    -0.65
    visor
    -0.65
    camp
    -0.63
    isSpecialOrderable
    -0.62
    BLE
    -0.62
    POSITIVE LOGITS
    ateral
    1.18
    oqu
    1.10
    apsed
    1.07
    ocation
    1.06
    ision
    1.05
    apse
    1.03
    iery
    1.03
    ider
    1.02
    ossus
    1.01
    ibrary
    0.98
    Activations Density 0.063%

    No Known Activations