© 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. 9-RES-JB
    11. 7294
    Prev
    Next
    INDEX
    Explanations

    phrases related to commands or instructions given by individuals

    oai_token-act-pair · gpt-3.5-turbo

    commands or phrases related to urgent situations and safety

    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
    20439
    -0.79
     quir
    -0.78
    etheless
    -0.71
     magnification
    -0.70
    mittedly
    -0.69
     anecd
    -0.68
    imilar
    -0.67
    everal
    -0.66
     Flavoring
    -0.66
    ynchron
    -0.64
    POSITIVE LOGITS
    !".
    1.71
    !",
    1.61
    !"
    1.56
    !'"
    1.46
    !!"
    1.42
    !'
    1.40
    !!
    1.20
    !
    1.18
    !!!!
    1.18
    ?!"
    1.16
    Activations Density 0.501%

    No Known Activations