© 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. 14454
    Prev
    Next
    INDEX
    Explanations

    contractions with apostrophes indicating omitted letters

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific character or symbol in the text

    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
     Voyager
    -0.72
     Droid
    -0.67
     board
    -0.67
     Lag
    -0.65
     ferry
    -0.64
     Kenyan
    -0.63
     Romance
    -0.63
     Libyan
    -0.62
     Pacific
    -0.62
     relay
    -0.61
    POSITIVE LOGITS
    ¹
    1.28
    º
    1.23
    ¬
    1.18
    £
    1.18
    Į
    1.17
    Ń
    1.17
    °
    1.12
    ª
    1.11
    ¦
    1.11
    ½
    1.11
    Activations Density 0.235%

    No Known Activations