© 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. 11-RES-JB
    11. 4970
    Prev
    Next
    INDEX
    Explanations

    internet URLs containing "https://" or "https://"

    oai_token-act-pair · gpt-3.5-turbo

    URLs or links in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dism
    -0.70
     Cutter
    -0.68
     Opportun
    -0.67
     Relief
    -0.67
     Opportunity
    -0.66
     ousted
    -0.66
     Viol
    -0.65
     defeats
    -0.65
     wrongly
    -0.65
     unfinished
    -0.65
    POSITIVE LOGITS
    twitter
    1.65
    t
    1.55
    youtu
    1.40
    www
    1.39
    medium
    1.26
    wik
    1.22
    doi
    1.18
    cdn
    1.16
    rss
    1.15
    archive
    1.14
    Activations Density 0.024%

    No Known Activations