© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12321
    Prev
    Next
    INDEX
    Explanations

    references to glass or glass-related objects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "glass" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Akin
    -0.78
     Ake
    -0.70
     Hussein
    -0.68
    ghan
    -0.65
     Statistical
    -0.64
    IRED
    -0.63
    Filename
    -0.63
     Hussain
    -0.63
    CVE
    -0.60
    ality
    -0.59
    POSITIVE LOGITS
    ware
    1.14
    door
    1.05
     beads
    0.98
     bottles
    0.97
     pane
    0.96
     shards
    0.95
     jars
    0.94
    glass
    0.92
     bead
    0.91
    works
    0.91
    Activations Density 0.028%

    No Known Activations