© 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. 22363
    Prev
    Next
    INDEX
    Explanations

    phrases relating to public services

    oai_token-act-pair · gpt-3.5-turbo

    references to public service-related content

    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
    jad
    -0.72
    assian
    -0.68
    thur
    -0.67
    yang
    -0.67
     Judd
    -0.67
    ãĥ¼ãĥĨ
    -0.62
    Pacific
    -0.62
    idental
    -0.60
    weet
    -0.60
     Yamato
    -0.60
    POSITIVE LOGITS
     agencies
    0.88
     announcements
    0.88
     broadcaster
    0.82
     initiatives
    0.80
     enterprises
    0.79
     institutions
    0.78
     campaigns
    0.76
     broadcasters
    0.75
     pamph
    0.72
     organisations
    0.71
    Activations Density 0.191%

    No Known Activations