© 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. 3233
    Prev
    Next
    INDEX
    Explanations

    calls to action to subscribe to newsletters or services

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscribing for newsletters or updates

    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
     ado
    -0.55
    eanor
    -0.53
    pedia
    -0.51
     theoret
    -0.51
     inexper
    -0.51
     rendition
    -0.51
    oshop
    -0.49
    soDeliveryDate
    -0.49
    NetMessage
    -0.49
    profits
    -0.48
    POSITIVE LOGITS
    ãĥ¼ãĤ¯
    0.59
     guiName
    0.59
     Cancel
    0.54
    lect
    0.54
     anymore
    0.53
     Courier
    0.53
    renheit
    0.53
    bleacher
    0.53
     POLITICO
    0.52
    dayName
    0.52
    Activations Density 0.017%

    No Known Activations