© 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. 10-RES-JB
    11. 20592
    Prev
    Next
    INDEX
    Explanations

    references to living in a specific environment or cultural context

    oai_token-act-pair · gpt-3.5-turbo

    references to societal conditions and cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fax
    -0.67
    iler
    -0.61
    oji
    -0.57
     circulate
    -0.57
     Released
    -0.56
    umar
    -0.56
    iso
    -0.55
     Registration
    -0.55
     accompanies
    -0.55
    assis
    -0.55
    POSITIVE LOGITS
     something
    1.10
     vastly
    1.00
     a
    0.97
     arguably
    0.97
     an
    0.96
     extraordinarily
    0.92
     incredibly
    0.91
     unparalleled
    0.91
     someone
    0.90
     exceptionally
    0.89
    Activations Density 0.419%

    No Known Activations