© 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. 9790
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessive pronouns

    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
    762
    +0.11
    0.5%
    481
    +0.11
    0.5%
    354
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.11
    0.10
    354
    +0.11
    0.08
    139
    +0.10
    0.07
    Negative Logits
    arios
    -0.83
    ãĥĩãĤ£
    -0.79
    ACP
    -0.74
    atana
    -0.66
    adobe
    -0.65
    irm
    -0.64
    grave
    -0.61
    CCC
    -0.60
    Plus
    -0.60
    atlantic
    -0.60
    POSITIVE LOGITS
     Majesty
    0.91
    mos
    0.79
     majesty
    0.78
     misunder
    0.75
     POV
    0.73
     asleep
    0.70
    're
    0.69
    'll
    0.69
     hooked
    0.68
     kindly
    0.67
    Activations Density 0.405%

    No Known Activations