© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5097
    Prev
    Next
    INDEX
    Explanations

    words related to domes and capsules

    oai_token-act-pair · gpt-3.5-turbo

    references to structures with curved shapes such as domes and cones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    went
    -0.83
    poll
    -0.75
     Dame
    -0.75
    aldo
    -0.73
    IGHTS
    -0.73
    ndra
    -0.71
    abet
    -0.70
    ĩ
    -0.70
    aldi
    -0.68
    ãģĹ
    -0.67
    POSITIVE LOGITS
     shaped
    0.85
     shape
    0.77
     prism
    0.76
    osite
    0.73
    ozo
    0.72
    iameter
    0.71
    shaped
    0.69
     cutter
    0.68
     depress
    0.67
    adena
    0.66
    Activations Density 0.064%

    No Known Activations