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. 45703
    Prev
    Next
    INDEX
    Explanations

    references to broadband services or related concepts

    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
    288
    +0.13
    0.6%
    67
    +0.10
    0.5%
    297
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.13
    0.01
    365
    +0.10
    0.01
    67
    +0.10
    0.01
    Negative Logits
     Oro
    -0.81
     Frankenstein
    -0.78
     Uriel
    -0.74
     Canaver
    -0.68
    illard
    -0.66
    arians
    -0.65
     Rubin
    -0.63
    ICAN
    -0.63
    omez
    -0.63
     Adolf
    -0.62
    POSITIVE LOGITS
    casting
    1.32
    casters
    1.21
    cast
    1.16
    caster
    1.16
    casts
    1.10
    sword
    1.06
    sheet
    1.03
    ening
    1.03
    bent
    1.00
    cut
    0.98
    Activations Density 0.004%

    No Known Activations