© 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 24576
    9. 8-RES_FS24576-JB
    11. 9265
    Prev
    Next
    INDEX
    Explanations

    words related to political figures and dynasties

    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
    +0.17
    0.8%
    503
    +0.11
    0.5%
    393
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.17
    0.04
    103
    +0.11
    0.04
    514
    +0.09
    0.03
    Negative Logits
     Strongh
    -0.66
     Exper
    -0.66
     Jem
    -0.66
    wagen
    -0.61
     Fut
    -0.60
     Fract
    -0.60
     Robbie
    -0.59
     Farming
    -0.59
     BBC
    -0.58
     Remem
    -0.57
    POSITIVE LOGITS
    ´
    1.35
    Ķ
    1.31
    Ļ
    1.29
    ¤
    1.26
    ª
    1.24
    ħ
    1.24
    ĩ
    1.22
    ¨
    1.21
    ĥ
    1.21
    ĸ
    1.20
    Activations Density 0.080%

    No Known Activations