© 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. 13602
    Prev
    Next
    INDEX
    Explanations

    words related to a specific proper noun "Ham."

    oai_token-act-pair · gpt-3.5-turbo

    references to Hamlet, specifically the text and themes associated with the play

    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
    uality
    -0.64
     Leone
    -0.61
     Kyoto
    -0.60
     Cardinal
    -0.60
    CLASSIFIED
    -0.59
     Kraken
    -0.59
    âĶĢâĶĢ
    -0.58
     misleading
    -0.57
     Staples
    -0.56
     Grind
    -0.56
    POSITIVE LOGITS
    mers
    1.31
    pton
    1.31
    pered
    1.26
    elin
    1.19
    ster
    1.16
    ilton
    1.16
    sterdam
    1.15
    pering
    1.14
    monds
    1.07
    sters
    1.04
    Activations Density 0.027%

    No Known Activations