© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5861
    Prev
    Next
    INDEX
    Explanations

    dimensions in the format of length x width

    oai_token-act-pair · gpt-3.5-turbo

    dimensions and specifications of display screens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kson
    -0.71
    virt
    -0.63
    uned
    -0.61
    veh
    -0.60
    chuk
    -0.60
    thro
    -0.59
    unes
    -0.59
    gob
    -0.59
    tha
    -0.59
    raise
    -0.59
    POSITIVE LOGITS
    izont
    0.68
     width
    0.67
     spacing
    0.66
     magnification
    0.66
     Width
    0.64
    ailability
    0.63
    ©¶æ¥µ
    0.62
     18
    0.62
     layout
    0.61
     768
    0.60
    Activations Density 0.018%

    No Known Activations