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

    Neuronpedia

    Jacobian LensNEW
    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. 14885
    Prev
    Next
    INDEX
    Explanations

    phrases related to causing harm or danger

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the imposition of burdens or pressures

    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
     experiences
    -0.77
    events
    -0.72
     matters
    -0.71
     revelations
    -0.71
    anism
    -0.70
     modes
    -0.69
     secrets
    -0.66
    projects
    -0.65
    anship
    -0.65
    settings
    -0.65
    POSITIVE LOGITS
     halt
    1.10
     lid
    1.09
     stop
    1.04
     moratorium
    1.03
     limit
    0.98
     disclaimer
    0.97
     spotlight
    0.97
     dent
    0.96
     ceiling
    0.96
     smile
    0.96
    Activations Density 0.067%

    No Known Activations