© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9449
    Prev
    Next
    INDEX
    Explanations

    keywords related to virtual voice assistants like Alexa and Siri

    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
    343
    +0.12
    0.6%
    289
    +0.11
    0.5%
    538
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.12
    0.02
    288
    +0.11
    0.02
    538
    +0.10
    0.01
    Negative Logits
    emate
    -0.96
    ers
    -0.86
    erm
    -0.85
    rar
    -0.81
    stead
    -0.80
    er
    -0.78
    ERAL
    -0.75
    iatus
    -0.74
    eral
    -0.73
    erry
    -0.72
    POSITIVE LOGITS
     Cortana
    0.74
     voic
    0.71
     fluent
    0.69
     voice
    0.69
    XM
    0.69
     Siri
    0.69
     speaker
    0.67
     microphone
    0.66
     microphones
    0.65
    TY
    0.65
    Activations Density 0.035%

    No Known Activations