© 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. 9-RES-JB
    11. 23553
    Prev
    Next
    INDEX
    Explanations

    medical terms related to fibrous tissues

    oai_token-act-pair · gpt-3.5-turbo

    references to the Fibonacci sequence and related mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.70
     spitting
    -0.69
     Sisters
    -0.68
     whiff
    -0.67
     bearer
    -0.65
     inh
    -0.63
     Canary
    -0.62
     Keeper
    -0.61
     chalk
    -0.60
     Darling
    -0.59
    POSITIVE LOGITS
    rous
    1.32
    romy
    1.22
    rative
    1.21
    ilit
    1.15
    raph
    1.14
    rosis
    1.11
    rocal
    1.10
    rical
    1.08
    rog
    1.07
    rator
    1.06
    Activations Density 0.101%

    No Known Activations