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 49152
    5. 8-RES_FS49152-JB
    6. 25574
    Prev
    Next
    INDEX
    Explanations

    terms related to licensing, particularly in the context of sports organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    48
    +0.13
    0.6%
    311
    +0.11
    0.5%
    339
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.13
    0.01
    746
    +0.11
    0.01
    48
    +0.10
    0.01
    Negative Logits
     Samoa
    -0.85
     Alma
    -0.76
     Forsaken
    -0.74
     Unch
    -0.73
     Canterbury
    -0.71
    ãĥ¯ãĥ³
    -0.70
     guiActiveUnfocused
    -0.70
     Lans
    -0.67
     Hole
    -0.67
     Hiroshima
    -0.67
    POSITIVE LOGITS
    ensing
    1.63
    enses
    1.45
    hess
    1.25
    enced
    1.20
    ensed
    1.19
    entious
    1.18
    ence
    1.18
    encing
    1.18
    ensor
    1.16
    ences
    1.14
    Activations Density 0.005%

    No Known Activations