© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 9487
    Prev
    Next
    INDEX
    Explanations

    keywords related to academic performance and academic settings

    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
    500
    +0.11
    0.5%
    300
    +0.10
    0.5%
    512
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.07
    500
    +0.10
    0.05
    78
    +0.10
    0.04
    Negative Logits
    omen
    -0.59
     Tick
    -0.55
    Synopsis
    -0.54
    xtap
    -0.54
    ============
    -0.54
    ========
    -0.51
     playbook
    -0.51
    ~~~~
    -0.50
     sugg
    -0.50
     festive
    -0.50
    POSITIVE LOGITS
     thereafter
    0.93
     elsewhere
    0.89
     herself
    0.78
     afterward
    0.77
     itself
    0.76
     themselves
    0.73
    ohm
    0.72
     himself
    0.71
     oneself
    0.70
     afterwards
    0.70
    Activations Density 0.577%

    No Known Activations