© 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. 2747
    Prev
    Next
    INDEX
    Explanations

    phrases related to caution or recommendation

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

    instances of the word "before" 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
    ãĤ·
    -0.76
    ãĤ©
    -0.75
    onet
    -0.73
    olit
    -0.73
    aez
    -0.73
    odied
    -0.73
    artisan
    -0.72
    atic
    -0.71
    aic
    -0.69
    ocry
    -0.69
    POSITIVE LOGITS
     proceeding
    1.42
     deciding
    1.22
     committing
    1.22
     diving
    1.18
     embark
    1.17
     concluding
    1.11
     submitting
    1.11
     attempting
    1.10
     commenting
    1.06
     initiating
    1.06
    Activations Density 0.082%

    No Known Activations