© 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. 11-RES-JB
    11. 7498
    Prev
    Next
    INDEX
    Explanations

    phrases related to well-wishing and greetings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant events or emotional responses in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ÅŁ
    -0.90
    ÄŁ
    -0.88
    qqa
    -0.88
    âĶ
    -0.86
     Erd
    -0.86
    udeau
    -0.86
     Raqqa
    -0.85
    NAT
    -0.82
    igrant
    -0.80
     rapists
    -0.79
    POSITIVE LOGITS
     Jerry
    2.20
    Jerry
    2.07
     Garcia
    1.58
     Bobby
    1.56
     Billy
    1.50
     Grateful
    1.43
    Billy
    1.43
     Jimmy
    1.42
     Ronnie
    1.36
     Johnny
    1.34
    Activations Density 0.186%

    No Known Activations