© 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 3072
    9. 8-RES_FS3072-JB
    11. 129
    Prev
    Next
    INDEX
    Explanations

    verbs indicating potential or possibility

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    745
    +0.10
    0.4%
    15
    +0.10
    0.4%
    394
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.10
    0.08
    8
    +0.10
    0.07
    38
    +0.10
    0.06
    Negative Logits
    ĸļ
    -0.88
     evidently
    -0.64
     exting
    -0.62
     invariably
    -0.62
     supposedly
    -0.61
    Initialized
    -0.61
    jab
    -0.59
    assembly
    -0.58
    verend
    -0.58
    ãĥ¼ãĥĨãĤ£
    -0.58
    POSITIVE LOGITS
     someday
    0.97
     underest
    0.89
     overest
    0.82
     misunder
    0.81
     typo
    0.80
     tempted
    0.77
     underestimated
    0.76
     recons
    0.74
     inadvertently
    0.74
     mistaken
    0.73
    Activations Density 1.705%

    No Known Activations