© 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 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. 8952
    Prev
    Next
    INDEX
    Explanations

    specific named entities or references, likely related to criticisms or evaluations of them

    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
    445
    +0.13
    0.6%
    373
    +0.10
    0.5%
    726
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.13
    0.02
    273
    +0.10
    0.02
    389
    +0.10
    0.02
    Negative Logits
     PID
    -0.70
     tro
    -0.69
    abal
    -0.63
     redes
    -0.61
     overrun
    -0.60
    arthy
    -0.60
     culminated
    -0.60
    gypt
    -0.59
     hurd
    -0.59
     suprem
    -0.58
    POSITIVE LOGITS
     sir
    0.86
    nor
    0.85
     nor
    0.84
    onsense
    0.83
     Nope
    0.80
    Nor
    0.77
    tons
    0.77
     Nor
    0.76
    None
    0.74
    æĪ
    0.73
    Activations Density 0.082%

    No Known Activations