© 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. 7-RES-JB
    11. 1656
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Beau" with varying activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Megan" or variations of it in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orative
    -0.63
    eyes
    -0.63
    appers
    -0.63
     Cavaliers
    -0.61
     Attribution
    -0.61
    APS
    -0.60
     flares
    -0.60
     selves
    -0.59
     GOODMAN
    -0.59
    Wallet
    -0.59
    POSITIVE LOGITS
    llah
    1.22
    gment
    1.08
    ction
    1.06
    qua
    1.04
    lette
    0.98
    fman
    0.92
    cel
    0.88
    lly
    0.87
    lla
    0.87
    cham
    0.87
    Activations Density 0.024%

    No Known Activations