© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7138
    Prev
    Next
    INDEX
    Explanations

    pronouns or reflexive pronouns indicating a focus on self-identity and individual perspective

    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
    324
    +0.11
    0.5%
    430
    +0.10
    0.4%
    759
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    324
    +0.11
    0.03
    391
    +0.10
    0.02
    759
    +0.10
    0.02
    Negative Logits
    olid
    -0.76
    rought
    -0.76
    emis
    -0.71
    onite
    -0.71
    rise
    -0.69
    orie
    -0.67
    iard
    -0.66
    pour
    -0.65
     Mub
    -0.64
    vine
    -0.64
    POSITIVE LOGITS
    é¾įåĸļ士
    0.84
     mate
    0.77
    selves
    0.73
     personally
    0.71
     creatively
    0.71
     selves
    0.69
    imei
    0.68
     profess
    0.67
    ternally
    0.66
    Redd
    0.65
    Activations Density 0.036%

    No Known Activations