Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23600
    Prev
    Next
    INDEX
    Explanations

    proper names or acronyms

    oai_token-act-pair · gpt-3.5-turbo

    names or identifiers of individuals and entities

    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
     Pen
    -0.91
     pen
    -0.89
     237
    -0.80
     Radar
    -0.80
     Noir
    -0.78
     Siren
    -0.77
     Rox
    -0.76
     RN
    -0.75
     FF
    -0.74
     pens
    -0.74
    POSITIVE LOGITS
    AND
    1.25
    ands
    1.17
    ande
    1.16
    and
    1.12
    anders
    1.11
    older
    1.04
    ander
    1.02
    anding
    0.99
    anda
    0.98
    anded
    0.98
    Activations Density 0.327%

    No Known Activations