© 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. 6-RES-JB
    11. 1494
    Prev
    Next
    INDEX
    Explanations

    transitions indicating sequence or order

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a sequence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alogy
    -0.78
    alog
    -0.70
    ãĤº
    -0.68
    under
    -0.59
    itability
    -0.58
    eker
    -0.58
    detail
    -0.57
    atts
    -0.57
    chio
    -0.56
    opic
    -0.55
    POSITIVE LOGITS
     dawn
    0.87
    iphany
    0.83
    cember
    0.82
    ruary
    0.82
     arrival
    0.81
     advent
    0.79
     dusk
    0.75
     fateful
    0.75
     sunset
    0.74
    imester
    0.73
    Activations Density 0.742%

    No Known Activations