© 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. 9-RES-JB
    11. 18490
    Prev
    Next
    INDEX
    Explanations

    metaphorical or literal mentions of glass or glass-related items

    oai_token-act-pair · gpt-3.5-turbo

    references to glass and related materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CVE
    -0.77
     Ake
    -0.73
    IRED
    -0.70
     Akin
    -0.69
    Filename
    -0.66
     NCT
    -0.63
    mins
    -0.63
    ften
    -0.63
    merce
    -0.63
    ired
    -0.62
    POSITIVE LOGITS
    door
    1.01
     shards
    0.99
     beads
    0.97
    gow
    0.96
    works
    0.95
     bottles
    0.92
    glass
    0.90
    loo
    0.89
    ware
    0.89
     bead
    0.88
    Activations Density 0.029%

    No Known Activations