© 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. 11-RES-JB
    11. 7711
    Prev
    Next
    INDEX
    Explanations

    phrases related to reaching a peak or record level

    oai_token-act-pair · gpt-3.5-turbo

    instances of reaching or hitting significant thresholds or milestones

    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
    thia
    -0.68
    ItemThumbnailImage
    -0.64
    Simple
    -0.63
    gnu
    -0.63
    blade
    -0.63
    alogue
    -0.61
    behind
    -0.60
    oved
    -0.59
    comings
    -0.59
    NEWS
    -0.59
    POSITIVE LOGITS
     saturation
    1.17
     parity
    1.08
     puberty
    1.08
     maturity
    1.02
     peak
    0.98
     equilibrium
    0.98
     milestones
    0.93
     heights
    0.92
     capacity
    0.89
     profitability
    0.87
    Activations Density 0.100%

    No Known Activations