© 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. 11107
    Prev
    Next
    INDEX
    Explanations

    geographical locations and associated information like joining dates and post counts from profiles

    oai_token-act-pair · gpt-3.5-turbo

    numeric values or identifiers associated with user profiles

    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
    endum
    -0.77
     appendix
    -0.72
    #$
    -0.71
    CVE
    -0.69
    soDeliveryDate
    -0.67
    *:
    -0.64
    ï¸ı
    -0.63
    ĵĺ
    -0.60
     surrendered
    -0.60
    —-
    -0.60
    POSITIVE LOGITS
     Posts
    1.57
    Posts
    0.84
     Never
    0.65
     Deaths
    0.64
     posts
    0.64
     Past
    0.63
     Moder
    0.63
    ategory
    0.63
     Username
    0.62
     Achievements
    0.62
    Activations Density 0.020%

    No Known Activations