© 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. 5328
    Prev
    Next
    INDEX
    Explanations

    URLs or web links

    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
    373
    +0.10
    0.5%
    195
    +0.10
    0.5%
    125
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.10
    0.02
    445
    +0.10
    0.02
    592
    +0.09
    0.02
    Negative Logits
     Adin
    -0.66
     Takeru
    -0.66
     Ori
    -0.64
     primitive
    -0.63
     Lisp
    -0.63
     saline
    -0.62
    ority
    -0.62
     Antar
    -0.61
     sided
    -0.61
     Software
    -0.61
    POSITIVE LOGITS
    www
    1.59
    youtu
    1.47
    imgur
    1.42
    twitter
    1.40
    goo
    1.16
    ://
    1.13
    cdn
    1.12
    natureconservancy
    1.10
    archive
    1.05
    redd
    1.01
    Activations Density 0.014%

    No Known Activations