© 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. 12440
    Prev
    Next
    INDEX
    Explanations

    words related to making promises or guarantees

    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
    354
    +0.12
    0.5%
    566
    +0.12
    0.5%
    183
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.07
    354
    +0.12
    0.07
    502
    +0.10
    0.07
    Negative Logits
    asma
    -0.70
    Marginal
    -0.70
    reens
    -0.67
    rising
    -0.66
     externalToEVAOnly
    -0.66
    burn
    -0.65
    endar
    -0.64
    etsk
    -0.63
     totality
    -0.63
    aults
    -0.62
    POSITIVE LOGITS
     recommend
    1.10
     Promise
    1.03
     promise
    0.95
     suggest
    0.94
    'm
    0.89
     guarantee
    0.87
     advise
    0.85
    'll
    0.84
     encourage
    0.76
     presume
    0.76
    Activations Density 0.216%

    No Known Activations