© 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. 12-RES-JB
    11. 4140
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical issues or errors

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating errors or issues with the system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    cott
    -0.76
    thora
    -0.76
    rounder
    -0.65
     weap
    -0.64
     sole
    -0.64
     lie
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.60
     sugg
    -0.59
    Forest
    -0.59
    illin
    -0.56
    POSITIVE LOGITS
    !
    0.78
     Newsletter
    0.77
    !:
    0.67
     retrieving
    0.66
     registering
    0.65
    !--
    0.65
    gs
    0.65
     Register
    0.63
     whilst
    0.63
     Reporting
    0.62
    Activations Density 0.048%

    No Known Activations