© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1811
    Prev
    Next
    INDEX
    Explanations

    web links or URLs with various formats

    oai_token-act-pair · gpt-3.5-turbo

    parts of web links and references to online content

    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
     oun
    -1.01
     swept
    -0.89
     pacing
    -0.88
     tough
    -0.86
     stiff
    -0.83
     deliber
    -0.82
     constrained
    -0.82
     wrinkles
    -0.82
     exha
    -0.81
     advancing
    -0.81
    POSITIVE LOGITS
    http
    2.20
    https
    2.10
    Advertisements
    1.97
    References
    1.64
    ================================================================
    1.62
    Links
    1.62
    www
    1.61
    License
    1.60
    Website
    1.60
    Wikipedia
    1.56
    Activations Density 0.301%

    No Known Activations