© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26803
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mulvaney."

    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
    496
    +0.15
    0.7%
    371
    +0.10
    0.5%
    151
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.01
    224
    +0.10
    0.01
    99
    +0.10
    0.01
    Negative Logits
    ivity
    -0.88
    ually
    -0.79
    icably
    -0.74
    ories
    -0.70
    iably
    -0.65
    iveness
    -0.65
    ently
    -0.65
    eries
    -0.63
    orer
    -0.62
    spring
    -0.62
    POSITIVE LOGITS
    geon
    0.92
    hyde
    0.92
    clips
    0.83
    berry
    0.81
    chan
    0.81
    combe
    0.78
    aney
    0.76
    croft
    0.73
    hawk
    0.73
    mson
    0.73
    Activations Density 0.009%

    No Known Activations