© 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. 1531
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and preferences

    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
    362
    +0.14
    0.6%
    385
    +0.13
    0.6%
    167
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.07
    385
    +0.13
    0.07
    62
    +0.11
    0.05
    Negative Logits
     apiece
    -0.82
    itect
    -0.81
    ibaba
    -0.72
    illac
    -0.69
     Uriel
    -0.69
     guiIcon
    -0.67
     respectively
    -0.66
    ãħĭ
    -0.66
    aphael
    -0.64
    arians
    -0.63
    POSITIVE LOGITS
    anmar
    1.29
     own
    1.23
    stery
    1.22
    opic
    1.18
    opia
    1.14
     favorite
    1.13
    ocard
    1.12
     wife
    1.09
     dad
    1.08
     husband
    1.06
    Activations Density 0.148%

    No Known Activations