© 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 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. 8-RES-JB
    11. 19386
    Prev
    Next
    INDEX
    Explanations

    terms related to architectural structures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "arch" in various contexts, particularly related to archbishops or archrivals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kamp
    -0.70
    TPS
    -0.66
    ggle
    -0.65
     Pearce
    -0.65
     charged
    -0.65
    ndra
    -0.64
     ABE
    -0.63
    vous
    -0.63
     Bach
    -0.62
    cers
    -0.62
    POSITIVE LOGITS
    itect
    1.51
    ipel
    1.49
    bishop
    1.16
    ival
    1.06
    adia
    1.04
    aic
    1.02
    ivist
    1.01
    angel
    0.99
    agon
    0.95
    mage
    0.94
    Activations Density 0.033%

    No Known Activations