© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10156
    Prev
    Next
    INDEX
    Explanations

    terms related to costs and technical specifications in a context discussing electronic devices or systems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    314
    +0.12
    0.5%
    118
    +0.10
    0.5%
    233
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.12
    0.07
    616
    +0.10
    0.06
    314
    +0.10
    0.00
    Negative Logits
     waivers
    -0.72
     Generator
    -0.72
     Dragons
    -0.71
     Knights
    -0.67
     Strike
    -0.66
     Consent
    -0.65
     Waves
    -0.65
     designation
    -0.65
     Writers
    -0.64
     Decoder
    -0.64
    POSITIVE LOGITS
    istent
    1.21
    isable
    1.20
    ivable
    1.16
    urable
    1.15
    able
    1.15
    iable
    1.15
    istic
    1.12
    worthy
    1.11
    ishable
    1.10
    vable
    1.09
    Activations Density 0.500%

    No Known Activations