© 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. 7715
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating evaluation or response to events

    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
     THAT
    -0.66
     incent
    -0.60
     folks
    -0.60
     THESE
    -0.57
    ixties
    -0.56
     THIS
    -0.56
    inese
    -0.56
    ividual
    -0.56
    inian
    -0.55
    Those
    -0.55
    POSITIVE LOGITS
     it
    0.85
     its
    0.79
     Its
    0.65
    Its
    0.64
     theirs
    0.62
    llah
    0.60
    its
    0.59
    uve
    0.59
    ADRA
    0.57
     Paddock
    0.57
    Activations Density 1.010%

    No Known Activations