© 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. 11-RES-JB
    11. 20714
    Prev
    Next
    INDEX
    Explanations

    words related to physical structures and constructions, like moat, canals, burrows, and buildings

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns related to structures or facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KNOWN
    -0.74
    ENSE
    -0.70
    Psy
    -0.69
    vez
    -0.65
    emort
    -0.64
    IFIED
    -0.63
    Money
    -0.63
    ONEY
    -0.63
    ITNESS
    -0.63
    ãĤ±
    -0.62
    POSITIVE LOGITS
     overlooking
    1.01
     erected
    1.00
    pipe
    0.98
    lain
    0.96
    lift
    0.93
    yards
    0.92
     beneath
    0.86
     containing
    0.86
     excav
    0.86
     empt
    0.86
    Activations Density 0.276%

    No Known Activations