© 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 3072
    5. 8-RES_FS3072-JB
    6. 130
    Prev
    Next
    INDEX
    Explanations

    mentions of the name 'Kevin'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    1
    +0.10
    0.5%
    311
    +0.10
    0.5%
    326
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.11
    288
    +0.10
    0.13
    232
    +0.09
    0.09
    Negative Logits
    minist
    -0.81
    ret
    -0.80
    onse
    -0.75
    ming
    -0.72
    bian
    -0.70
    resso
    -0.70
    meric
    -0.69
    daq
    -0.67
    mitted
    -0.65
    reg
    -0.65
    POSITIVE LOGITS
    ifully
    0.83
    ificent
    0.82
    ature
    0.82
    ory
    0.78
    IGHTS
    0.78
    aido
    0.77
    arios
    0.76
    Ĵ
    0.76
    iful
    0.76
    ãĥĦ
    0.75
    Activations Density 1.586%

    No Known Activations