© 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. 4673
    Prev
    Next
    INDEX
    Explanations

    words related to sugary fluids and their consumption, as well as medical conditions associated with them

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

    instances of the substring "su" in various 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
     Monroe
    -0.67
     Strauss
    -0.65
     everywhere
    -0.62
     Moody
    -0.62
     explaining
    -0.60
     gulf
    -0.59
     Thib
    -0.59
     responding
    -0.59
     inquiries
    -0.58
     privately
    -0.58
    POSITIVE LOGITS
    gary
    1.55
    fficiency
    1.42
    prisingly
    1.35
    prise
    1.31
    ffic
    1.28
    prises
    1.24
    ds
    1.21
    zanne
    1.18
    asion
    1.16
    nder
    1.15
    Activations Density 0.011%

    No Known Activations