© 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. 1608
    Prev
    Next
    INDEX
    Explanations

    uppercase words or proper names

    oai_token-act-pair · gpt-3.5-turbo

    uppercase letters and specific letter combinations

    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
     Kush
    -0.61
    NEWS
    -0.55
    DX
    -0.55
    VL
    -0.54
    yip
    -0.52
    enegger
    -0.52
    +.
    -0.51
     liking
    -0.51
     FISA
    -0.51
    VII
    -0.50
    POSITIVE LOGITS
    acies
    0.67
    anism
    0.64
    acious
    0.63
    agons
    0.61
    atism
    0.60
    angles
    0.60
    itized
    0.58
    icial
    0.58
    istically
    0.58
    igroup
    0.58
    Activations Density 0.214%

    No Known Activations