© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 1574
    Prev
    Next
    INDEX
    Explanations

    rooms or spaces where personal or significant events have taken place

    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
    481
    +0.11
    0.5%
    180
    +0.10
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.11
    0.05
    352
    +0.10
    0.05
    288
    +0.10
    0.05
    Negative Logits
    anson
    -0.82
    laus
    -0.74
    hig
    -0.71
    arnaev
    -0.71
    uador
    -0.65
    annot
    -0.64
    inge
    -0.63
     oneself
    -0.63
    utorial
    -0.62
    erest
    -0.62
    POSITIVE LOGITS
    mates
    0.95
    mate
    0.90
     mates
    0.86
     balcony
    0.85
     mate
    0.80
     drawer
    0.75
     courtyard
    0.73
     lair
    0.72
     stash
    0.72
     doorstep
    0.72
    Activations Density 0.207%

    No Known Activations