© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 17094
    Prev
    Next
    INDEX
    Explanations

    adjectives describing emotions or judgments

    oai_token-act-pair · gpt-3.5-turbo

    discussions about controversial or unsettling topics

    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
    umbn
    -0.82
    rongh
    -0.78
    foreseen
    -0.75
    execute
    -0.74
    ocument
    -0.71
    cele
    -0.71
    sylvania
    -0.71
    mediately
    -0.70
    obook
    -0.69
    ufact
    -0.68
    POSITIVE LOGITS
     huh
    1.49
     eh
    1.41
     tho
    1.04
    ?!
    1.01
    !
    1.00
    !!
    0.95
    !?
    0.95
     ya
    0.92
     ðŁĺ
    0.85
     kidding
    0.84
    Activations Density 0.525%

    No Known Activations