© 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. 4320
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events related to wars or conflicts

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

    negative sentiments and criticisms

    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
    ð
    -0.60
    ãĥĺãĥ©
    -0.52
    /
    -0.51
    âĶģ
    -0.50
    """
    -0.48
    âĢł
    -0.48
     diaper
    -0.47
    ãĥ´ãĤ¡
    -0.47
    isSpecialOrderable
    -0.47
     condom
    -0.47
    POSITIVE LOGITS
    ne
    0.59
    ay
    0.53
    no
    0.52
    OHN
    0.48
    iak
    0.46
     Mist
    0.46
     Dal
    0.46
     Errors
    0.46
    min
    0.45
    na
    0.45
    Activations Density 1.160%

    No Known Activations