© 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. 1-RES-JB
    11. 21362
    Prev
    Next
    INDEX
    Explanations

    examples or mentions of items or entities that fall under a category

    oai_token-act-pair · gpt-3.5-turbo

    phrases that mention examples or items within a broader category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ath
    -0.80
    ²¾
    -0.75
    ATH
    -0.70
    uay
    -0.69
    rait
    -0.69
    ocracy
    -0.68
    athi
    -0.67
    ocratic
    -0.67
    cel
    -0.67
    ython
    -0.66
    POSITIVE LOGITS
    including
    0.88
     INCLUD
    0.79
    ãĤ´
    0.78
    among
    0.75
    minus
    0.74
     including
    0.72
     Accessories
    0.70
    lished
    0.70
     GOODMAN
    0.68
     hypoc
    0.67
    Activations Density 0.049%

    No Known Activations