© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4942
    Prev
    Next
    INDEX
    Explanations

    information related to community services and resources

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    terms related to government and community services

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Travels
    -0.78
     Tata
    -0.76
     Roose
    -0.75
     Countries
    -0.73
     Notting
    -0.71
    Foreign
    -0.70
     Whilst
    -0.69
     Britons
    -0.69
    ONDON
    -0.69
    xit
    -0.68
    POSITIVE LOGITS
     district
    1.30
     board
    1.26
     commissioners
    1.26
     commissioner
    1.25
     superintendent
    1.24
     districts
    1.17
     department
    1.16
     supervisor
    1.15
     examiner
    1.14
     supervisors
    1.13
    Activations Density 0.281%

    No Known Activations