© 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. 730
    Prev
    Next
    INDEX
    Explanations

    information about events, initiatives, and projects related to various cities and communities

    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
    481
    +0.13
    0.6%
    641
    +0.11
    0.5%
    127
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    641
    +0.13
    0.13
    225
    +0.11
    0.12
    620
    +0.10
    0.03
    Negative Logits
    nesty
    -0.79
    pload
    -0.76
    imester
    -0.70
    ":""},{"
    -0.68
    ¿½
    -0.66
    endment
    -0.65
    starter
    -0.64
    ayne
    -0.63
    ©¶æ¥µ
    -0.62
     caveat
    -0.62
    POSITIVE LOGITS
     topics
    0.99
     themes
    0.93
     perspectives
    0.93
     lifestyles
    0.91
     landscapes
    0.91
     interact
    0.85
     viewpoints
    0.85
     facets
    0.82
     personalities
    0.82
     everyday
    0.81
    Activations Density 3.890%

    No Known Activations