© 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. 20604
    Prev
    Next
    INDEX
    Explanations

    number ranges

    oai_token-act-pair · gpt-3.5-turbo

    numeric representations related to film or music collections

    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
     slur
    -0.63
     polit
    -0.62
     Gawker
    -0.62
     SERVICE
    -0.61
     Wikimedia
    -0.61
     PubMed
    -0.60
     Null
    -0.60
    initialized
    -0.60
     Pastebin
    -0.58
     aroused
    -0.58
    POSITIVE LOGITS
     episodes
    1.19
    episode
    1.08
     installments
    1.00
     chapters
    0.95
     minute
    0.95
    quel
    0.94
    CD
    0.93
    minute
    0.92
     episode
    0.90
    inch
    0.90
    Activations Density 0.126%

    No Known Activations