© 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. 1301
    Prev
    Next
    INDEX
    Explanations

    job titles or names of public figures

    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
    15
    +0.12
    0.5%
    11
    +0.10
    0.5%
    119
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.04
    288
    +0.10
    0.05
    326
    +0.10
    0.04
    Negative Logits
    acular
    -0.91
    orius
    -0.77
    ition
    -0.76
    orative
    -0.72
    uously
    -0.68
    eele
    -0.68
    uality
    -0.68
    igm
    -0.67
    oshenko
    -0.65
    heses
    -0.65
    POSITIVE LOGITS
    ancock
    0.78
    idays
    0.76
    mong
    0.75
    aida
    0.73
    IGH
    0.72
    iland
    0.71
    ospital
    0.70
    ISTORY
    0.70
    aday
    0.70
    ttp
    0.68
    Activations Density 0.146%

    No Known Activations