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 24576
    5. 8-RES_FS24576-JB
    6. 8852
    Prev
    Next
    INDEX
    Explanations

    information related to economic hardships and financial vulnerabilities

    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
    102
    +0.22
    1.1%
    55
    +0.15
    0.7%
    208
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.22
    0.15
    55
    +0.15
    0.13
    566
    +0.09
    0.08
    Negative Logits
     Ends
    -0.82
    inav
    -0.77
     Telesc
    -0.72
     sums
    -0.69
     Benefits
    -0.69
    onnaissance
    -0.69
     Moines
    -0.69
     Want
    -0.68
    isions
    -0.68
     yells
    -0.67
    POSITIVE LOGITS
     currently
    1.19
    nt
    1.13
     unlikely
    1.12
     still
    1.10
     presently
    1.09
     likely
    1.04
     not
    1.02
     now
    1.02
     slated
    1.01
     supposed
    1.00
    Activations Density 0.507%

    No Known Activations