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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20772
    Prev
    Next
    INDEX
    Explanations

    terms related to academia and education

    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
    57
    +0.15
    0.7%
    377
    +0.11
    0.5%
    718
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.15
    0.02
    326
    +0.11
    0.01
    659
    +0.10
    0.01
    Negative Logits
    come
    -0.72
    nets
    -0.72
    gro
    -0.72
    theless
    -0.72
    liness
    -0.71
    ledge
    -0.70
     Jenner
    -0.70
    ographs
    -0.67
    falls
    -0.67
    orius
    -0.67
    POSITIVE LOGITS
    HHHH
    0.95
    BIL
    0.89
    ccess
    0.88
    BILITIES
    0.88
    HR
    0.84
    HAHAHAHA
    0.84
    HAHA
    0.83
    BILITY
    0.82
    BA
    0.82
    ZE
    0.81
    Activations Density 0.022%

    No Known Activations