© 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. 12293
    Prev
    Next
    INDEX
    Explanations

    words related to preferences or choices

    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
    276
    +0.14
    0.6%
    496
    +0.12
    0.5%
    101
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.14
    0.02
    349
    +0.12
    0.02
    61
    +0.11
    0.02
    Negative Logits
    brance
    -1.01
    gren
    -0.70
    idem
    -0.70
    orig
    -0.68
    breakers
    -0.67
    arta
    -0.66
    interrupted
    -0.66
    infeld
    -0.65
    bish
    -0.64
    breaker
    -0.63
    POSITIVE LOGITS
    rals
    0.84
     embodiments
    0.81
     anonymity
    0.75
    ably
    0.71
     embodiment
    0.68
     endings
    0.65
     preferring
    0.64
     solitude
    0.63
     simplicity
    0.60
     alternative
    0.60
    Activations Density 0.022%

    No Known Activations