© 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 24576
    9. 8-RES_FS24576-JB
    11. 9750
    Prev
    Next
    INDEX
    Explanations

    text related to the concept of "attachment" and its implications on existence and reality

    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
    480
    +0.23
    1.2%
    762
    +0.12
    0.6%
    351
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.23
    0.06
    762
    +0.12
    0.09
    570
    +0.12
    0.02
    Negative Logits
    soDeliveryDate
    -0.95
    çīĪ
    -0.84
    audi
    -0.80
    senal
    -0.79
    cussion
    -0.73
    Rail
    -0.71
    BuyableInstoreAndOnline
    -0.65
     Inspector
    -0.65
    editor
    -0.64
    ortium
    -0.64
    POSITIVE LOGITS
     oneself
    0.95
     uncond
    0.87
     abstract
    0.84
     imperfect
    0.84
     intrinsically
    0.84
     finite
    0.83
     bodily
    0.80
     intellect
    0.79
     observable
    0.79
     outward
    0.77
    Activations Density 1.070%

    No Known Activations