© 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. 6-RES-JB
    11. 9694
    Prev
    Next
    INDEX
    Explanations

    medical and anatomical terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "sy-" or "Sy-" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORED
    -0.79
    inarily
    -0.71
    DERR
    -0.69
    wagen
    -0.66
    arding
    -0.64
    ãģ®éŃĶ
    -0.64
     Hots
    -0.64
    UGH
    -0.63
    ardless
    -0.62
    ãĥ¼ãĥĨãĤ£
    -0.62
    POSITIVE LOGITS
    mbol
    1.48
    ntax
    1.24
    thia
    1.18
    nerg
    1.11
    philis
    1.10
    nergy
    1.09
    bil
    1.07
    racuse
    0.99
    ptoms
    0.99
    rup
    0.97
    Activations Density 0.028%

    No Known Activations