© 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. 11-RES-JB
    11. 3379
    Prev
    Next
    INDEX
    Explanations

    keywords related to indexing, such as "index," used in a technical or financial context

    oai_token-act-pair · gpt-3.5-turbo

    references to indices in various contexts

    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
    soDeliveryDate
    -0.79
    uggage
    -0.74
    zech
    -0.72
     Argon
    -0.69
    overs
    -0.66
    amera
    -0.65
    sei
    -0.64
    rier
    -0.61
    creen
    -0.60
    athed
    -0.60
    POSITIVE LOGITS
     finger
    0.90
     mund
    0.88
    ing
    0.86
    ation
    0.86
    ysis
    0.84
    uary
    0.80
    ical
    0.78
    ieth
    0.77
    alist
    0.77
    er
    0.76
    Activations Density 0.063%

    No Known Activations