© 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. 4058
    Prev
    Next
    INDEX
    Explanations

    items or objects mentioned in a list

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

    references to specific characters or items in a narrative context

    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
     quotas
    -0.73
     Saturdays
    -0.71
     Indies
    -0.68
     Crosby
    -0.67
     Woodward
    -0.67
     Consumers
    -0.65
    reports
    -0.65
     miscar
    -0.65
     Joyce
    -0.65
    renheit
    -0.64
    POSITIVE LOGITS
     costume
    1.61
     armor
    1.47
     torso
    1.44
     cape
    1.43
     helmet
    1.42
     outfit
    1.42
     armour
    1.35
     Costume
    1.29
     attire
    1.28
     goggles
    1.24
    Activations Density 0.464%

    No Known Activations