© 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. 20494
    Prev
    Next
    INDEX
    Explanations

    the mention of alcoholic beverages in the form of bottles

    oai_token-act-pair · gpt-3.5-turbo

    references to bottles, particularly in the context of beverages

    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
    merce
    -0.87
    doms
    -0.78
    urities
    -0.73
    uli
    -0.69
    yrinth
    -0.69
    IFA
    -0.68
    tale
    -0.67
    ahime
    -0.65
    adesh
    -0.63
    undai
    -0.63
    POSITIVE LOGITS
     bottles
    1.17
     bottle
    1.15
     Bottle
    0.99
    Bott
    0.93
     Bott
    0.89
     opener
    0.89
    mark
    0.82
     labelled
    0.82
     refill
    0.80
     vodka
    0.80
    Activations Density 0.027%

    No Known Activations