© 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. 1217
    Prev
    Next
    INDEX
    Explanations

    specific years or time periods

    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
    40
    +0.13
    0.6%
    699
    +0.11
    0.5%
    206
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.13
    0.06
    526
    +0.11
    -0.01
    206
    +0.10
    0.05
    Negative Logits
    interstitial
    -0.68
     reiterate
    -0.62
     NAD
    -0.62
    antam
    -0.60
    undrum
    -0.59
    Nit
    -0.59
    othermal
    -0.59
    ERAL
    -0.58
    eeper
    -0.57
    anges
    -0.57
    POSITIVE LOGITS
     earlier
    1.24
     yesterday
    1.17
     previous
    1.13
     last
    1.07
     beforehand
    1.05
     ago
    1.04
     prior
    1.00
    terday
    0.96
     preceding
    0.91
     originally
    0.89
    Activations Density 1.434%

    No Known Activations