© 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 EvalsExportsinterp-engineNEWAPI 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. 5577
    Prev
    Next
    INDEX
    Explanations

    words related to technology, specifically terms related to AP (Access Point) configurations and settings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "AP," likely referring to the Associated Press or related content

    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
    terday
    -0.68
     roy
    -0.62
    catch
    -0.61
    glers
    -0.60
     fry
    -0.60
     thumbs
    -0.60
     stabil
    -0.59
     regress
    -0.57
     scrolling
    -0.57
    gaard
    -0.56
    POSITIVE LOGITS
    PLE
    1.31
    PLIC
    1.29
    PLIED
    1.27
    TN
    1.22
    PLA
    1.20
    PROV
    1.18
    PRO
    1.14
    OE
    1.14
    Cs
    1.12
    PE
    1.10
    Activations Density 0.025%

    No Known Activations