© 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. 7-RES-JB
    11. 12556
    Prev
    Next
    INDEX
    Explanations

    mention of pubs or related activities and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to pubs or public houses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gaia
    -0.73
     Archangel
    -0.73
     EFF
    -0.71
    IRD
    -0.70
    llor
    -0.70
     GOODMAN
    -0.68
     Soros
    -0.67
    OHN
    -0.67
    ylum
    -0.66
     Reson
    -0.66
    POSITIVE LOGITS
    lique
    1.39
    lish
    1.36
    lishing
    1.35
    lisher
    1.25
    lishes
    1.24
    escent
    1.22
    lik
    1.06
    bing
    1.05
    cers
    0.96
    bed
    0.94
    Activations Density 0.033%

    No Known Activations