© 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. 3350
    Prev
    Next
    INDEX
    Explanations

    transitional phrases indicating contrast or continuation

    oai_token-act-pair · gpt-3.5-turbo

    inverted commas or quotation marks

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.83
    SourceFile
    -0.83
    ULAR
    -0.75
    oodle
    -0.70
    ãĤ©
    -0.68
    obyl
    -0.67
    Widget
    -0.66
    MpServer
    -0.65
    acho
    -0.64
    apest
    -0.63
    POSITIVE LOGITS
     unlike
    1.13
     despite
    1.08
     although
    0.98
     contrary
    0.98
     according
    0.97
     there
    0.97
     since
    0.94
     if
    0.92
     owing
    0.92
     whereas
    0.89
    Activations Density 0.184%

    No Known Activations