© 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. 2036
    Prev
    Next
    INDEX
    Explanations

    keywords related to user reviews and ratings

    oai_token-act-pair · gpt-3.5-turbo

    elements of user profile information and ratings

    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
     financing
    -0.96
     textbooks
    -0.85
     strengthening
    -0.84
     fundra
    -0.84
     museums
    -0.83
     closure
    -0.82
     subsequent
    -0.82
     visitation
    -0.82
     ÂŃ
    -0.81
     fulfilling
    -0.80
    POSITIVE LOGITS
    Magikarp
    1.43
    guy
    1.40
    Gamer
    1.40
    Gaming
    1.40
    Guy
    1.40
    Fan
    1.35
    Knight
    1.34
    Wolf
    1.33
    gamer
    1.31
    Nin
    1.29
    Activations Density 0.246%

    No Known Activations