© 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. 1498
    Prev
    Next
    INDEX
    Explanations

    words related to political figures or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to "amb" or related terms, likely indicating a focus on events or discussions surrounding the ambassador or ambassadorial context

    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
     detector
    -0.66
     AGA
    -0.64
     detectors
    -0.63
     wart
    -0.62
     dormant
    -0.60
     cele
    -0.60
     stub
    -0.58
     resent
    -0.58
     Zi
    -0.57
     bailed
    -0.57
    POSITIVE LOGITS
    uilding
    1.21
    urger
    1.19
    lesh
    1.05
    assador
    1.04
    assadors
    1.03
    erella
    1.00
    uild
    1.00
    rian
    0.93
    urg
    0.93
    ique
    0.93
    Activations Density 0.033%

    No Known Activations