© 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 12288
    5. 8-RES_FS12288-JB
    6. 708
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal reactions and emotions

    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
    407
    +0.11
    0.5%
    426
    +0.10
    0.5%
    414
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.11
    0.06
    377
    +0.10
    0.07
    718
    +0.10
    0.06
    Negative Logits
    winner
    -0.66
     plurality
    -0.65
    prev
    -0.64
     Practices
    -0.63
    Delivery
    -0.63
     sanitation
    -0.62
    entry
    -0.62
     Manufacturing
    -0.62
     Vale
    -0.61
     Directions
    -0.61
    POSITIVE LOGITS
     wonder
    1.25
     chuckle
    1.20
     wondering
    1.19
     cringe
    1.19
     shudder
    1.16
     incred
    1.13
     nause
    1.12
     amaz
    1.11
     disbelief
    1.10
     awe
    1.09
    Activations Density 0.811%

    No Known Activations