© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19353
    Prev
    Next
    INDEX
    Explanations

    information related to locations and venues, such as addresses, event details, and historical background

    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
    183
    +0.15
    0.7%
    506
    +0.10
    0.5%
    491
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.15
    0.01
    183
    +0.10
    0.01
    506
    +0.10
    0.01
    Negative Logits
    anism
    -0.78
    heny
    -0.72
    irements
    -0.71
    issance
    -0.71
    ION
    -0.70
    ions
    -0.69
    sburgh
    -0.68
    asca
    -0.67
    tics
    -0.66
    ttle
    -0.65
    POSITIVE LOGITS
    hog
    1.01
     Catalyst
    0.98
     rusher
    0.94
     edge
    0.88
    combe
    0.81
    phal
    0.80
    Edge
    0.77
     guarding
    0.76
    bite
    0.74
    kick
    0.71
    Activations Density 0.025%

    No Known Activations