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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 8726
    Prev
    Next
    INDEX
    Explanations

    references to physical objects made of glass

    oai_token-act-pair · gpt-3.5-turbo

    instances of glass mentioned in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Express
    -0.76
    IRED
    -0.74
    AF
    -0.73
    ired
    -0.68
    days
    -0.68
    ETA
    -0.67
    DAY
    -0.67
    unct
    -0.66
    ften
    -0.66
     Cosponsors
    -0.66
    POSITIVE LOGITS
    glass
    1.22
     glass
    1.15
     shards
    1.09
     bottles
    1.02
     glasses
    0.99
     beads
    0.93
     champagne
    0.93
     bead
    0.88
     pane
    0.87
    Glass
    0.86
    Activations Density 0.009%

    No Known Activations