© 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. 16010
    Prev
    Next
    INDEX
    Explanations

    terms related to thoughts and beliefs, particularly those associated with delusions, stereotypes, and fears

    oai_token-act-pair · gpt-3.5-turbo

    themes related to mental and social constructs, particularly those involving delusions and stereotypes

    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
    asus
    -0.85
    gre
    -0.70
    Operation
    -0.64
    eligible
    -0.64
    amen
    -0.63
    emale
    -0.62
    Veter
    -0.61
    entin
    -0.61
    bilt
    -0.61
    mobi
    -0.60
    POSITIVE LOGITS
     about
    1.34
     concerning
    1.22
     regarding
    1.18
     ABOUT
    1.17
     pertaining
    1.07
    mith
    1.00
     relating
    0.97
     About
    0.94
     revolving
    0.94
     abound
    0.92
    Activations Density 0.229%

    No Known Activations