© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2604
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and related procedural steps in mathematical operations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mathematical or programming expressions and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    advertising
    -0.48
     moot
    -0.48
     replay
    -0.42
     pest
    -0.42
     confirmation
    -0.42
     backlash
    -0.42
     speculation
    -0.41
     junk
    -0.40
     obscurity
    -0.40
     grun
    -0.40
    POSITIVE LOGITS
     represents
    1.01
     denotes
    0.97
     comprises
    0.97
     consists
    0.95
     belongs
    0.94
     includes
    0.93
     are
    0.92
     contains
    0.92
     is
    0.92
     corresponds
    0.90
    Activations Density 0.744%

    No Known Activations