© 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. 20989
    Prev
    Next
    INDEX
    Explanations

    statements or direct speech

    oai_token-act-pair · gpt-3.5-turbo

    quoted responses or statements

    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
     torpedo
    -0.73
     Sussex
    -0.65
     overturned
    -0.63
     Newark
    -0.63
     Newport
    -0.63
     pigeon
    -0.61
    irable
    -0.59
     maritime
    -0.59
     Borders
    -0.58
     disadvantage
    -0.58
    POSITIVE LOGITS
    âĢ
    2.00
     âĢ
    1.91
     «
    1.29
    ãĢĮ
    1.28
     "âĢ¦
    1.27
    ãĢ
    1.24
     Â
    1.24
    ãĢİ
    1.24
     "@
    1.19
     "'
    1.19
    Activations Density 0.260%

    No Known Activations