© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 8528
    Prev
    Next
    INDEX
    Explanations

    content related to legality, safety, and terms of service

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with legality and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndum
    -0.60
    tons
    -0.55
    soever
    -0.53
     Downs
    -0.53
    ÄŁ
    -0.51
    reau
    -0.51
     Mississ
    -0.49
     coli
    -0.49
     Borders
    -0.48
     crim
    -0.47
    POSITIVE LOGITS
     metic
    0.61
    Untitled
    0.61
    Static
    0.59
    ò
    0.58
    ThumbnailImage
    0.58
    ActionCode
    0.57
     celeb
    0.56
    Asset
    0.56
    ļéĨĴ
    0.55
    oreAnd
    0.55
    Activations Density 0.226%

    No Known Activations