© 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. 10730
    Prev
    Next
    INDEX
    Explanations

    phrases related to putting things together or organizing information

    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
    167
    +0.10
    0.4%
    677
    +0.09
    0.4%
    724
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.10
    0.02
    724
    +0.09
    0.02
    501
    +0.09
    0.01
    Negative Logits
    anwhile
    -0.73
    den
    -0.69
     Reporter
    -0.66
    antis
    -0.65
    terness
    -0.65
    azed
    -0.65
    YE
    -0.64
    amon
    -0.64
    00000
    -0.63
     opened
    -0.62
    POSITIVE LOGITS
     makeshift
    0.76
     anew
    0.70
     sketches
    0.69
     rudimentary
    0.67
    ilts
    0.66
    ãĤ¤ãĥĪ
    0.65
     playlist
    0.65
     playable
    0.64
     nifty
    0.63
     nicely
    0.63
    Activations Density 0.026%

    No Known Activations