© 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. 7738
    Prev
    Next
    INDEX
    Explanations

    technology companies and countries in a global context

    oai_token-act-pair · gpt-3.5-turbo

    statements affirming the existence or significance of entities or concepts

    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
    urry
    -0.70
    aturdays
    -0.69
    pleted
    -0.68
    ļéĨĴ
    -0.67
     Include
    -0.65
    plings
    -0.64
    Timeout
    -0.64
    sed
    -0.63
     circulate
    -0.62
    ussions
    -0.62
    POSITIVE LOGITS
     certainly
    1.27
     undoubtedly
    1.24
     undeniably
    1.16
     definitely
    1.12
     hardly
    1.11
     arguably
    1.09
     unquestion
    1.09
     surely
    1.08
     uniquely
    1.05
     clearly
    1.04
    Activations Density 0.294%

    No Known Activations