© 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. 6244
    Prev
    Next
    INDEX
    Explanations

    contractions of 'is' and phrases indicating an action or opinion

    oai_token-act-pair · gpt-3.5-turbo

    statements of opinion or assertion, particularly those involving the verb "to be."

    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
    roman
    -0.77
    rod
    -0.73
    76561
    -0.72
    ukong
    -0.69
    ffe
    -0.66
    ãĤ©
    -0.65
    ãĥĺãĥ©
    -0.64
    ipl
    -0.63
    ases
    -0.60
    link
    -0.60
    POSITIVE LOGITS
     imperative
    1.40
     incumbent
    1.25
     uncons
    1.13
     unacceptable
    1.06
     irresponsible
    1.06
     vital
    1.03
     important
    1.01
     unfortunate
    1.00
     impossible
    1.00
     unethical
    0.99
    Activations Density 0.142%

    No Known Activations