© 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. 3516
    Prev
    Next
    INDEX
    Explanations

    claims or statements of certainty

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

    references to controversial or debatable statements and assertions

    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
    nton
    -0.82
     contrace
    -0.64
     Carbuncle
    -0.64
    thumbnails
    -0.60
    Tips
    -0.60
    tar
    -0.60
     Spoiler
    -0.58
     marquee
    -0.58
    isoft
    -0.57
    bid
    -0.57
    POSITIVE LOGITS
    orial
    0.92
     leve
    0.86
     leveled
    0.85
     about
    0.85
     made
    0.85
    ulence
    0.81
    fulness
    0.81
    ulent
    0.81
     regarding
    0.79
     against
    0.76
    Activations Density 0.076%

    No Known Activations