© 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. 8-RES-JB
    11. 17750
    Prev
    Next
    INDEX
    Explanations

    addresses and location-related information

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to health organizations and their addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zens
    -0.73
    cation
    -0.72
    sbm
    -0.70
    ecause
    -0.64
    bugs
    -0.64
    ggle
    -0.64
     WATCHED
    -0.63
     binge
    -0.62
    ikers
    -0.61
     worrying
    -0.61
    POSITIVE LOGITS
    ;;;;;;;;;;;;
    1.04
     Dept
    1.03
     âĵĺ
    0.94
     Retrieved
    0.93
     Ltd
    0.89
     Died
    0.89
     pg
    0.86
     Website
    0.82
     Version
    0.81
     2100
    0.78
    Activations Density 0.454%

    No Known Activations