© 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. 11-RES-JB
    11. 20556
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or conditions occurring after some significant point in time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "post" followed by numbers or specific contexts

    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
     Qiao
    -0.76
     Bett
    -0.65
     Beans
    -0.62
     materially
    -0.58
     precincts
    -0.56
     misunderstood
    -0.56
    onge
    -0.55
     Faul
    -0.55
     bands
    -0.55
    Ø©
    -0.55
    POSITIVE LOGITS
    mortem
    1.41
    graduate
    1.31
    doctoral
    1.30
    gres
    1.28
    cards
    1.28
    modern
    1.23
    secondary
    1.21
    ulates
    1.19
    hum
    1.18
    natal
    1.16
    Activations Density 0.029%

    No Known Activations