© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13673
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific event or program called "Embarcadero."

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular advertisement or promotional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ideshow
    -0.72
     slack
    -0.63
     priceless
    -0.61
     cytok
    -0.60
     unsub
    -0.59
     sloppy
    -0.59
     plagiar
    -0.57
     shaky
    -0.57
     unmist
    -0.57
     limp
    -0.57
    POSITIVE LOGITS
    venture
    1.24
    ventures
    1.15
    ynam
    1.07
    visor
    1.04
    rome
    1.03
    aily
    1.03
    ahime
    1.02
    visors
    1.00
    oodle
    0.98
    elta
    0.97
    Activations Density 0.037%

    No Known Activations