© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 19061
    Prev
    Next
    INDEX
    Explanations

    verbs associated with chaotic or messy environments

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to confinement or enclosure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.60
     Consortium
    -0.60
     Daylight
    -0.58
     CoC
    -0.57
     appropriation
    -0.56
    Reward
    -0.55
     Terms
    -0.55
     Passage
    -0.55
     Archdemon
    -0.55
    Champ
    -0.55
    POSITIVE LOGITS
     neatly
    1.09
     atop
    1.03
     beneath
    0.96
     prominently
    0.94
     onto
    0.92
     across
    0.92
     underneath
    0.88
     horizontally
    0.87
     snug
    0.86
     firmly
    0.85
    Activations Density 0.165%

    No Known Activations