Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 974
    Prev
    Next
    INDEX
    Explanations

    words related to sound and noise

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    380
    +0.13
    0.6%
    148
    +0.10
    0.4%
    289
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.10
    288
    +0.10
    0.12
    289
    +0.10
    0.02
    Negative Logits
    sis
    -0.71
     Leap
    -0.67
    ahime
    -0.66
     Illust
    -0.65
     Expend
    -0.64
     Inquisition
    -0.63
     Lann
    -0.63
    anova
    -0.62
    abad
    -0.62
    entin
    -0.61
    POSITIVE LOGITS
     voices
    1.16
     louder
    1.13
     sounded
    1.06
     recordings
    1.01
     heard
    1.01
     noises
    0.97
     voic
    0.95
    sound
    0.95
     deaf
    0.94
     audible
    0.94
    Activations Density 2.386%

    No Known Activations