© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11421
    Prev
    Next
    INDEX
    Explanations

    webpage elements that can be interacted with (e.g., sharing buttons, click to print)

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to media and streaming content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.82
    eatures
    -0.77
    packing
    -0.77
    orem
    -0.71
    WARE
    -0.67
    accompan
    -0.67
     reconc
    -0.67
    ihara
    -0.67
    interstitial
    -0.64
    brids
    -0.64
    POSITIVE LOGITS
     unknown
    0.66
     UV
    0.66
     iT
    0.62
     ultraviolet
    0.60
     Naj
    0.60
     mourn
    0.59
     quantity
    0.59
    amac
    0.58
    _
    0.58
    ^
    0.57
    Activations Density 0.095%

    No Known Activations