© 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. 41130
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Post" in various forms

    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
    321
    +0.13
    0.6%
    710
    +0.13
    0.6%
    166
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.13
    0.02
    710
    +0.13
    0.02
    433
    +0.10
    0.02
    Negative Logits
    IBLE
    -0.82
     Qiao
    -0.73
     Brill
    -0.72
    OSH
    -0.67
    èª
    -0.66
    OTS
    -0.65
    itability
    -0.65
     unaff
    -0.60
    issan
    -0.59
     bands
    -0.59
    POSITIVE LOGITS
    gres
    1.48
    greSQL
    1.42
    erity
    1.21
    mortem
    1.19
    doctoral
    1.16
    graduate
    1.02
    modern
    1.01
    natal
    0.99
    master
    0.96
    hum
    0.92
    Activations Density 0.018%

    No Known Activations