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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1800
    Prev
    Next
    INDEX
    Explanations

    information about regulations and safety precautions, particularly related to events on a campus

    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
    481
    +0.12
    0.6%
    745
    +0.10
    0.4%
    737
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.12
    0.05
    570
    +0.10
    0.01
    79
    +0.09
    0.04
    Negative Logits
     epigen
    -0.92
    ģĸ
    -0.89
     Nobel
    -0.85
     genome
    -0.84
    olkien
    -0.82
     prophecy
    -0.77
     genius
    -0.77
     genomic
    -0.76
    fortune
    -0.76
     powerhouse
    -0.76
    POSITIVE LOGITS
     restrooms
    1.25
     sidewalks
    1.25
     indoors
    1.18
     entrances
    1.17
     parking
    1.16
    iquette
    1.14
     toilets
    1.14
     outdoors
    1.13
     pedestrians
    1.12
     tresp
    1.10
    Activations Density 0.878%

    No Known Activations