© 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. 3833
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles related to individuals, organizations, and locations

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

    important titles and roles related to authority figures and institutions

    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
     occur
    -0.65
     mean
    -0.63
     ARE
    -0.59
    're
    -0.58
     abound
    -0.55
     influence
    -0.53
     include
    -0.52
     happen
    -0.51
     involve
    -0.50
     cause
    -0.50
    POSITIVE LOGITS
     teasp
    1.18
     reacts
    1.07
     investigates
    1.03
    ú
    1.02
    ě
    1.02
    ù
    1.02
    ē
    1.02
    ö
    1.02
    À
    1.02
     prepares
    1.02
    Activations Density 0.738%

    No Known Activations