© 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. 11-RES-JB
    11. 21094
    Prev
    Next
    INDEX
    Explanations

    words related to commercial businesses with the suffix "er", such as "Banker", "Theater", and "Searcher"

    oai_token-act-pair · gpt-3.5-turbo

    words ending in "er."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.91
    scl
    -0.65
     unders
    -0.62
    e
    -0.62
    ersen
    -0.60
     resid
    -0.60
     Lovecraft
    -0.59
    âĢ¢âĢ¢
    -0.59
    ĪĴ
    -0.57
     endeavour
    -0.57
    POSITIVE LOGITS
    adish
    1.13
    idge
    1.07
    jee
    1.06
    usalem
    0.99
    nery
    0.98
    unning
    0.94
    lein
    0.94
    ilee
    0.87
    wald
    0.85
    haps
    0.84
    Activations Density 0.103%

    No Known Activations