© 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. 7613
    Prev
    Next
    INDEX
    Explanations

    sentences containing contractions (e.g., "it's", "that's") and possessive forms (e.g., "people's", "car's")

    oai_token-act-pair · gpt-3.5-turbo

    affirmations and statements of existence

    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©
    -0.85
    arbon
    -0.84
    EStream
    -0.74
    ãĤ¼ãĤ¦ãĤ¹
    -0.74
    erning
    -0.74
    onds
    -0.72
    interstitial
    -0.70
    velop
    -0.68
    20439
    -0.66
    estones
    -0.66
    POSITIVE LOGITS
     bullshit
    1.14
     irrelevant
    1.12
     okay
    1.10
     alright
    1.10
     ok
    1.08
     ridiculous
    1.07
     pointless
    1.07
     disrespectful
    1.04
     unacceptable
    1.04
     fine
    1.01
    Activations Density 0.182%

    No Known Activations