© 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. 20562
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to events like news headlines or urgent messages

    oai_token-act-pair · gpt-3.5-turbo

    topics related to emergencies and significant societal issues

    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
    ranch
    -0.68
    é¾į
    -0.61
     tremend
    -0.60
     princ
    -0.59
     redirected
    -0.58
     aph
    -0.57
    rats
    -0.57
    channelAvailability
    -0.56
     flyers
    -0.56
     legends
    -0.56
    POSITIVE LOGITS
     02
    1.73
     01
    1.67
     03
    1.66
     04
    1.60
     00
    1.57
     05
    1.55
     06
    1.50
     07
    1.41
     08
    1.39
     09
    1.31
    Activations Density 0.026%

    No Known Activations