© 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. 3185
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and food poisoning, particularly focusing on types of bacteria and symptoms like diarrhea

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

    references to specific diseases or medical conditions

    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
    LINE
    -0.59
    EMENT
    -0.58
    liners
    -0.57
     IST
    -0.54
    INESS
    -0.53
    INGS
    -0.53
     Malk
    -0.53
    NEY
    -0.52
    liner
    -0.52
     OPS
    -0.52
    POSITIVE LOGITS
    a
    2.75
    as
    1.30
    aan
    1.26
    aa
    1.23
    ae
    1.20
    aq
    1.20
    aah
    1.16
    aic
    1.15
    aaa
    1.13
    aea
    1.08
    Activations Density 0.379%

    No Known Activations