© 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. 3730
    Prev
    Next
    INDEX
    Explanations

    phrases related to teamwork and community involvement

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

    mentions and discussions of community engagement and teamwork efforts

    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´ãĤ¡
    -0.74
     teasp
    -0.66
    +.
    -0.65
    `.
    -0.64
    $.
    -0.64
    ļéĨĴ
    -0.61
    !.
    -0.59
    ().
    -0.59
    %.
    -0.58
     pione
    -0.58
    POSITIVE LOGITS
     is
    1.56
     depends
    1.55
     isn
    1.49
     involves
    1.47
     constitutes
    1.46
     varies
    1.43
     requires
    1.42
     doesn
    1.41
     seems
    1.40
     implies
    1.39
    Activations Density 1.013%

    No Known Activations