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. 939
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or strong emotions

    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
    87
    +0.15
    0.8%
    218
    +0.15
    0.8%
    464
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.15
    -0.13
    218
    +0.15
    0.09
    326
    +0.14
    0.26
    Negative Logits
     policymakers
    -0.74
    ielding
    -0.68
    quartered
    -0.66
    asury
    -0.64
     markedly
    -0.63
     strikingly
    -0.62
     outset
    -0.62
     broadly
    -0.61
     incumbent
    -0.61
    Footnote
    -0.61
    POSITIVE LOGITS
     ;)
    1.34
     fuckin
    1.32
     haha
    1.24
     kinda
    1.21
     lol
    1.20
     :)
    1.18
     shit
    1.18
     :(
    1.17
     bitch
    1.15
    !!!!!
    1.14
    Activations Density 10.318%

    No Known Activations