© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1423
    Prev
    Next
    INDEX
    Explanations

    specific pronouns and verb forms related to ownership or obligation

    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
    410
    +0.12
    0.6%
    129
    +0.10
    0.5%
    412
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.12
    0.03
    410
    +0.10
    0.03
    601
    +0.10
    0.02
    Negative Logits
    Ĥİ
    -0.72
    eta
    -0.64
    assisted
    -0.64
    ufact
    -0.63
    eros
    -0.63
    inqu
    -0.62
     ascert
    -0.60
     Recomm
    -0.60
     ensured
    -0.60
    angan
    -0.59
    POSITIVE LOGITS
     firsthand
    0.89
     VIDEOS
    0.87
     unfold
    0.86
     therapist
    0.82
     similarities
    0.82
     resemblance
    0.79
     replay
    0.76
     psychiatrist
    0.74
     similarity
    0.74
     positives
    0.73
    Activations Density 0.205%

    No Known Activations