© 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. 20799
    Prev
    Next
    INDEX
    Explanations

    mentions of physical objects or concepts related to clothing

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "pantheon."

    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
    ï¸ı
    -0.76
    SPONSORED
    -0.73
     Dism
    -0.68
    ptions
    -0.68
     Jav
    -0.66
    ISSION
    -0.63
    sided
    -0.63
     Confederacy
    -0.61
     Covenant
    -0.60
    mit
    -0.58
    POSITIVE LOGITS
    heon
    1.68
    ry
    1.17
    ograph
    1.02
    hers
    0.99
    her
    0.98
    ograp
    0.94
    ries
    0.92
    agraph
    0.91
    alo
    0.91
    rag
    0.91
    Activations Density 0.041%

    No Known Activations