© 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. 3488
    Prev
    Next
    INDEX
    Explanations

    keywords related to academic research and publications

    oai_token-act-pair · gpt-3.5-turbo

    academic references or citations in research texts

    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
    ntil
    -0.70
    azor
    -0.70
    iously
    -0.67
    ilon
    -0.66
    aye
    -0.66
    chery
    -0.66
    anka
    -0.66
     aliases
    -0.66
     workaround
    -0.65
    jriwal
    -0.64
    POSITIVE LOGITS
     Retrieved
    1.41
     Proceedings
    1.32
     Journal
    1.19
     Perspect
    1.18
     PLoS
    1.16
     Oxford
    1.07
     Cambridge
    1.06
     Princeton
    1.04
     pp
    1.02
     Trends
    1.01
    Activations Density 0.114%

    No Known Activations