© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 7605
    Prev
    Next
    INDEX
    Explanations

    references to shapes or forms

    oai_token-act-pair · gpt-3.5-turbo

    references to "shape" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Labor
    -0.71
    comed
    -0.62
    Tickets
    -0.62
    audi
    -0.61
    ieth
    -0.61
    Auto
    -0.61
    allo
    -0.60
     Tickets
    -0.60
    HCR
    -0.59
    had
    -0.59
    POSITIVE LOGITS
     shape
    3.99
    shape
    2.91
     shapes
    2.63
     Shape
    2.45
     shaped
    2.07
    Shape
    1.73
     shaping
    1.63
    shaped
    1.53
     form
    1.43
     silhouette
    1.30
    Activations Density 0.021%

    No Known Activations