© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 45829
    Prev
    Next
    INDEX
    Explanations

    words related to forms and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    124
    +0.10
    0.5%
    26
    +0.10
    0.5%
    508
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.10
    0.01
    284
    +0.10
    0.01
    232
    +0.09
    0.01
    Negative Logits
     frag
    -0.68
    ++++++++
    -0.66
    prints
    -0.64
    ching
    -0.64
    BLIC
    -0.62
     franc
    -0.62
     Maya
    -0.58
    âĸ¬
    -0.58
    lder
    -0.57
    etsk
    -0.57
    POSITIVE LOGITS
    ammu
    0.93
    ont
    0.92
    orph
    0.90
    ingo
    0.90
    s
    0.90
    sg
    0.89
    etheus
    0.89
    essage
    0.87
    orm
    0.86
    yss
    0.84
    Activations Density 0.003%

    No Known Activations