© 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 12288
    9. 8-RES_FS12288-JB
    11. 9823
    Prev
    Next
    INDEX
    Explanations

    phrases related to life-threatening situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    248
    +0.11
    0.5%
    633
    +0.11
    0.5%
    95
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    633
    +0.11
    0.03
    152
    +0.11
    0.04
    147
    +0.09
    0.03
    Negative Logits
     Cosponsors
    -0.93
    aye
    -0.82
    Ey
    -0.76
    asio
    -0.76
    BLIC
    -0.70
    -+-+
    -0.66
    Invalid
    -0.64
     Cree
    -0.64
    gomery
    -0.64
    ulhu
    -0.63
    POSITIVE LOGITS
     expectancy
    0.87
     sciences
    0.81
    wreck
    0.76
    saving
    0.75
     breathing
    0.73
    termin
    0.73
     dignity
    0.71
     breat
    0.70
    consuming
    0.69
    eat
    0.69
    Activations Density 0.245%

    No Known Activations