© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 24576
    9. 8-RES_FS24576-JB
    11. 17393
    Prev
    Next
    INDEX
    Explanations

    verbs expressing hypothetical situations or outcomes

    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
    551
    +0.10
    0.4%
    223
    +0.10
    0.4%
    47
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.10
    0.07
    139
    +0.10
    0.05
    690
    +0.09
    0.04
    Negative Logits
    ials
    -0.66
     citing
    -0.65
     Conference
    -0.64
     Crom
    -0.61
     Cec
    -0.58
     queen
    -0.57
     Mell
    -0.56
    ament
    -0.56
    ions
    -0.55
    hea
    -0.53
    POSITIVE LOGITS
     culmin
    0.92
     accompany
    0.82
     propel
    0.81
     satisfy
    0.81
     underpin
    0.80
     someday
    0.79
     translate
    0.78
     expose
    0.78
     involve
    0.78
     contribute
    0.77
    Activations Density 0.165%

    No Known Activations