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. 1273
    Prev
    Next
    INDEX
    Explanations

    information about construction projects and urban planning, including topics like zoning, development issues, and the use of wind turbines in building design

    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
    +0.49
    2.5%
    447
    +0.21
    1.1%
    266
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.49
    -0.00
    305
    +0.21
    0.06
    30
    +0.10
    0.03
    Negative Logits
    Appearance
    -0.57
    issance
    -0.57
    deen
    -0.57
    ifestyle
    -0.57
    boot
    -0.55
    amaru
    -0.54
     Extras
    -0.53
    Optional
    -0.53
    igion
    -0.52
    whatever
    -0.52
    POSITIVE LOGITS
     recently
    0.81
     famously
    0.81
     2009
    0.62
    otom
    0.61
     publicized
    0.61
     unsuccessfully
    0.60
     boycot
    0.59
     reported
    0.59
     example
    0.58
     infamous
    0.57
    Activations Density 1.430%

    No Known Activations