© 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. 12148
    Prev
    Next
    INDEX
    Explanations

    numbers and codes mixed with text

    oai_token-act-pair · gpt-3.5-turbo

    medical terms and references to patient data

    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
    ciating
    -0.72
    DonaldTrump
    -0.65
    ighty
    -0.62
    lease
    -0.60
    chin
    -0.55
    actionDate
    -0.55
    footed
    -0.55
     heck
    -0.55
    urtles
    -0.55
    VERTISEMENT
    -0.53
    POSITIVE LOGITS
    /
    2.46
    /,
    2.07
    /_
    2.03
    /"
    1.96
    /)
    1.96
    /(
    1.95
    /.
    1.93
    /?
    1.91
    /#
    1.87
    /-
    1.81
    Activations Density 0.207%

    No Known Activations