© 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. 10-RES-JB
    11. 18698
    Prev
    Next
    INDEX
    Explanations

    phrases related to websites

    oai_token-act-pair · gpt-3.5-turbo

    references to websites

    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
    channelAvailability
    -0.67
    rived
    -0.66
    ients
    -0.62
     overpower
    -0.61
    skilled
    -0.61
    ersen
    -0.60
    OVER
    -0.60
    MQ
    -0.59
     deepening
    -0.59
    ogenic
    -0.58
    POSITIVE LOGITS
     www
    1.12
     homepage
    1.04
     page
    0.95
     webpage
    0.88
     website
    0.84
    pages
    0.84
     site
    0.83
     HERE
    0.80
     http
    0.77
     listing
    0.74
    Activations Density 0.051%

    No Known Activations