© 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 EvalsExportsAPI 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. 9-RES-JB
    11. 14756
    Prev
    Next
    INDEX
    Explanations

    short verbs that involve thorough investigation or understanding

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dig" and its variations, indicating actions related to excavation or searching

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.69
     constitu
    -0.67
     Leilan
    -0.64
    âĹ¼
    -0.63
    --------------------------------
    -0.61
    âĢ¢âĢ¢
    -0.58
    cream
    -0.57
    Reloaded
    -0.57
     Targ
    -0.55
     redistributed
    -0.55
    POSITIVE LOGITS
    itial
    1.16
    ested
    1.14
    ging
    1.12
    raph
    1.09
    gers
    1.08
     trenches
    1.07
    ress
    1.06
    ression
    1.06
    ests
    0.99
     dug
    0.95
    Activations Density 0.049%

    No Known Activations