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 49152
    5. 8-RES_FS49152-JB
    6. 25897
    Prev
    Next
    INDEX
    Explanations

    events, conferences, and gatherings of various types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    447
    +0.23
    1.1%
    481
    +0.16
    0.8%
    677
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.06
    677
    +0.16
    0.04
    749
    +0.11
    0.04
    Negative Logits
     looph
    -0.72
    lip
    -0.67
    poor
    -0.65
    obe
    -0.64
    lying
    -0.61
     Cogn
    -0.59
    é¾įå
    -0.58
    interest
    -0.58
     uninsured
    -0.58
    uyomi
    -0.57
    POSITIVE LOGITS
     attendees
    1.33
     organisers
    1.31
     organizers
    1.30
    goers
    1.22
     attendance
    1.16
    ivals
    1.09
     organizer
    1.05
     venue
    1.01
     festivities
    1.00
     event
    0.98
    Activations Density 0.219%

    No Known Activations