© 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. 0-RES-JB
    11. 8188
    Prev
    Next
    INDEX
    Explanations

    phrases related to gaps or spaces that need to be filled

    oai_token-act-pair · gpt-3.5-turbo

    references to gaps or deficiencies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alty
    -0.66
    sei
    -0.62
    ict
    -0.62
     tame
    -0.61
     Entertainment
    -0.61
    amed
    -0.60
    1001
    -0.60
     OK
    -0.60
     namesake
    -0.59
    brand
    -0.59
    POSITIVE LOGITS
     gaps
    3.97
     gap
    2.45
     discrepancies
    1.90
     loopholes
    1.89
     holes
    1.83
    gap
    1.79
     disparities
    1.72
     inconsistencies
    1.71
     cracks
    1.62
     Gap
    1.61
    Activations Density 0.015%

    No Known Activations