© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24116
    Prev
    Next
    INDEX
    Explanations

    commands or actions related to software manipulation or system configuration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to uninstallation or removal processes

    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
     Mothers
    -0.89
     Doctors
    -0.77
     Norn
    -0.72
     Teach
    -0.71
     Tut
    -0.70
     fame
    -0.70
     vocal
    -0.67
     Birth
    -0.67
     Faith
    -0.67
     Aboriginal
    -0.65
    POSITIVE LOGITS
    config
    1.24
    install
    1.24
    buff
    1.19
    rolling
    1.17
    initial
    1.17
    blocking
    1.15
    pack
    1.15
    ordered
    1.15
    assemb
    1.12
    serial
    1.12
    Activations Density 0.087%

    No Known Activations