© 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. 11-RES-JB
    11. 20863
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "check" in various forms and contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "che" within various contexts, particularly related to food and distinct items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    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_pre
    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
     belonging
    -0.66
     immersion
    -0.60
     Kingdoms
    -0.59
    DEBUG
    -0.57
    arium
    -0.55
     forth
    -0.54
    Assembly
    -0.54
    ANS
    -0.54
     WOR
    -0.54
    ness
    -0.53
    POSITIVE LOGITS
    wy
    0.94
    wed
    0.90
    ques
    0.87
    que
    0.83
    aters
    0.81
    ocobo
    0.78
    cedes
    0.77
    ws
    0.75
    efe
    0.75
    von
    0.74
    Activations Density 0.023%

    No Known Activations