© 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. 12-RES-JB
    11. 3685
    Prev
    Next
    INDEX
    Explanations

    proper names and entities mentioned in news articles

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

    references to specific individuals or names associated with notable events or contexts

    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
    tains
    -0.64
     Flavoring
    -0.64
    utters
    -0.61
    grades
    -0.61
    needs
    -0.59
     affects
    -0.59
     DOES
    -0.58
     fades
    -0.58
     decreases
    -0.57
     demands
    -0.57
    POSITIVE LOGITS
     respectively
    1.17
     discuss
    1.04
     collaborate
    1.03
     are
    1.02
     were
    1.01
     jointly
    1.01
     both
    0.99
     collide
    0.97
    both
    0.96
     argue
    0.96
    Activations Density 0.283%

    No Known Activations