© 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. 2-RES-JB
    11. 17620
    Prev
    Next
    INDEX
    Explanations

    references to an organization or acronym "IB" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to intelligence agencies and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cthulhu
    -0.85
    panic
    -0.76
    wich
    -0.73
     Hiroshima
    -0.71
     recess
    -0.70
    child
    -0.70
    mere
    -0.69
    sea
    -0.68
     Copenhagen
    -0.66
     Scandinavian
    -0.66
    POSITIVE LOGITS
    IB
    1.13
    terness
    1.00
    ANY
    0.99
    EW
    0.95
    ilib
    0.94
    JJ
    0.93
    ANE
    0.92
    FU
    0.92
    BB
    0.88
    BM
    0.88
    Activations Density 0.007%

    No Known Activations