© 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. 1583
    Prev
    Next
    INDEX
    Explanations

    information related to medical conditions and outbreaks

    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
    265
    +0.13
    0.6%
    483
    +0.10
    0.5%
    742
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    742
    +0.13
    0.03
    265
    +0.10
    0.04
    335
    +0.10
    0.03
    Negative Logits
    iture
    -0.94
    soDeliveryDate
    -0.83
    itures
    -0.82
    cknow
    -0.81
    selage
    -0.80
    )=(
    -0.76
     srfAttach
    -0.73
    HUD
    -0.72
    issance
    -0.71
    endars
    -0.70
    POSITIVE LOGITS
     infection
    1.73
     virus
    1.67
     infections
    1.66
     pathogens
    1.56
     toxin
    1.54
     viruses
    1.51
     bacter
    1.50
    infect
    1.50
     bacteria
    1.49
     Virus
    1.48
    Activations Density 0.242%

    No Known Activations