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

    Neuronpedia

    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. 21746
    Prev
    Next
    INDEX
    Explanations

    historical or original information related to a topic

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "originally" indicating the initial conditions or plans related to various subjects

    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
    =-=-=-=-=-=-=-=-
    -0.74
    rom
    -0.74
    vg
    -0.70
    omical
    -0.69
     Flavoring
    -0.68
    -+-+
    -0.68
    cig
    -0.67
    illin
    -0.66
     Awakens
    -0.66
    toggle
    -0.63
    POSITIVE LOGITS
     conceived
    1.26
     slated
    1.19
     intended
    1.16
     envisioned
    1.11
     planned
    1.10
     scheduled
    1.07
     designed
    0.97
     envis
    0.96
     posted
    0.95
     formulated
    0.94
    Activations Density 0.034%

    No Known Activations