© 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
    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. 1820
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethics, morality, and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern or apprehension regarding social or legal issues

    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
    ãĤ´ãĥ³
    -0.70
    BuyableInstoreAndOnline
    -0.66
     Bunker
    -0.63
     Doodle
    -0.61
     Slug
    -0.59
    ague
    -0.58
    ãĤ»
    -0.57
     Few
    -0.57
    antine
    -0.57
    odore
    -0.56
    POSITIVE LOGITS
     maybe
    1.15
     somebody
    1.03
     somehow
    1.01
     gonna
    0.97
     sort
    0.90
     uh
    0.89
     potentially
    0.88
     kind
    0.86
     kinda
    0.85
    maybe
    0.85
    Activations Density 0.597%

    No Known Activations