© 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. 41150
    Prev
    Next
    INDEX
    Explanations

    terms related to isolation and its effects

    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
    756
    +0.14
    0.6%
    288
    +0.12
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.14
    0.01
    756
    +0.12
    0.00
    288
    +0.10
    0.01
    Negative Logits
    orah
    -0.93
    enegger
    -0.89
    ãĥ£
    -0.84
    mington
    -0.77
    ãĥ¥
    -0.75
    ¶ħ
    -0.63
     eminent
    -0.62
    afort
    -0.62
    Benz
    -0.61
    bilt
    -0.61
    POSITIVE LOGITS
    ism
    1.18
    ists
    0.99
    ist
    0.96
     isolation
    0.88
    aries
    0.84
    istic
    0.82
    ary
    0.82
    ously
    0.82
     confinement
    0.80
    ively
    0.79
    Activations Density 0.008%

    No Known Activations