© 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. 9824
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic downturns and technical failures

    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
    481
    +0.12
    0.6%
    98
    +0.11
    0.5%
    493
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.12
    0.08
    551
    +0.11
    0.06
    566
    +0.10
    0.06
    Negative Logits
     Likes
    -0.69
     ILCS
    -0.65
    asonic
    -0.65
     specificity
    -0.65
    20439
    -0.64
     Wem
    -0.63
    umeric
    -0.62
    fortable
    -0.62
     hypotheses
    -0.61
    etz
    -0.61
    POSITIVE LOGITS
     mysteriously
    1.34
     vanished
    1.29
     disinteg
    1.28
     malfunction
    1.26
     tragically
    1.25
     collapsed
    1.23
     crumbling
    1.23
     vanish
    1.20
     collapsing
    1.19
     disappeared
    1.19
    Activations Density 1.033%

    No Known Activations