© 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. 21600
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to institutions or places of varying significance

    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
    akia
    -0.71
    igned
    -0.68
    hemer
    -0.62
    Synopsis
    -0.62
    venants
    -0.62
    tein
    -0.60
    iatus
    -0.60
    ottesville
    -0.59
    pection
    -0.57
    allowed
    -0.57
    POSITIVE LOGITS
     any
    1.30
     whoever
    1.24
     anything
    1.23
     anybody
    1.23
     anywhere
    1.22
     whatever
    1.20
     anyone
    1.16
    acle
    1.15
     whichever
    1.10
    whatever
    1.08
    Activations Density 0.158%

    No Known Activations