© 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. 8-RES-JB
    11. 2572
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce a shift in focus or provide context for a subsequent statement

    oai_token-act-pair · gpt-3.5-turbo

    references to illumination or clarity in the context of discussions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lycer
    -0.74
    irie
    -0.74
    irlf
    -0.72
    pload
    -0.70
    itals
    -0.68
    sis
    -0.68
    asus
    -0.68
    hesive
    -0.66
    kefeller
    -0.65
     Carnegie
    -0.65
    POSITIVE LOGITS
    enment
    1.02
    ening
    0.89
     circumstances
    0.85
     questioning
    0.80
    ened
    0.78
    weights
    0.76
    weight
    0.73
     circumstance
    0.73
    bringer
    0.72
    lessness
    0.68
    Activations Density 0.016%

    No Known Activations