© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 2252
    Prev
    Next
    INDEX
    Explanations

    information related to events, meetings, and schedules

    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
    749
    +0.14
    0.6%
    309
    +0.12
    0.6%
    677
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.14
    0.07
    749
    +0.12
    0.06
    89
    +0.10
    0.04
    Negative Logits
    oak
    -0.67
     antibodies
    -0.64
    hood
    -0.64
     corrections
    -0.63
     Species
    -0.63
    ãģķ
    -0.63
     weaknesses
    -0.62
    Wiki
    -0.61
     untreated
    -0.60
     journals
    -0.59
    POSITIVE LOGITS
     scheduled
    1.26
     hosted
    1.22
     attended
    1.12
     postponed
    1.09
     billed
    1.08
     convened
    1.08
     underway
    1.05
     conducted
    1.04
     televised
    1.04
     EVENT
    1.03
    Activations Density 0.484%

    No Known Activations