© 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. 24414
    Prev
    Next
    INDEX
    Explanations

    references to subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    instances of newsletter subscriptions and related terms

    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
    ãĤ´ãĥ³
    -0.67
     helicop
    -0.59
    endum
    -0.56
    rem
    -0.54
     throats
    -0.53
     lia
    -0.53
     sum
    -0.52
     dime
    -0.52
     lou
    -0.50
    WHERE
    -0.50
    POSITIVE LOGITS
     Tradable
    0.66
     Show
    0.66
     guiActiveUnfocused
    0.64
     Registration
    0.61
     Sunrise
    0.56
    Registration
    0.55
    ocus
    0.55
     isEnabled
    0.54
    leep
    0.54
     externalToEVAOnly
    0.53
    Activations Density 0.028%

    No Known Activations