© 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. 2533
    Prev
    Next
    INDEX
    Explanations

    words related to casinos and breweries

    oai_token-act-pair · gpt-3.5-turbo

    references to casinos and breweries

    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
    yon
    -0.90
     Helpful
    -0.88
    pring
    -0.74
    20439
    -0.74
     Marketable
    -0.72
    andum
    -0.71
    roxy
    -0.71
    lihood
    -0.71
    vich
    -0.70
     Grimoire
    -0.69
    POSITIVE LOGITS
     occupancy
    0.98
     owner
    0.93
     annex
    0.89
     operator
    0.88
     operated
    0.86
     entrances
    0.86
    goers
    0.86
     owners
    0.85
     entrance
    0.85
     hopping
    0.84
    Activations Density 0.184%

    No Known Activations