© 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. 11-RES-JB
    6. 22089
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an obvious or expected statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating inevitability or necessity

    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
    ational
    -0.78
    hiba
    -0.65
    sic
    -0.64
    nostic
    -0.59
    early
    -0.57
     retri
    -0.57
    olation
    -0.56
    etic
    -0.55
    alys
    -0.55
    tones
    -0.55
    POSITIVE LOGITS
     SAY
    1.05
     say
    0.98
     Says
    0.90
     thank
    0.86
     Saying
    0.81
    Say
    0.77
     thanked
    0.75
     said
    0.74
     says
    0.74
     saying
    0.73
    Activations Density 0.399%

    No Known Activations