© 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. 11-RES-JB
    11. 21471
    Prev
    Next
    INDEX
    Explanations

    phrases related to extremes or intense actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases concerning extreme conditions or limits

    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
    rolled
    -0.67
    zilla
    -0.66
    vich
    -0.64
    imar
    -0.64
    soDeliveryDate
    -0.64
    isters
    -0.63
    sburgh
    -0.62
    together
    -0.61
    CLASSIFIED
    -0.60
    TPPStreamerBot
    -0.59
    POSITIVE LOGITS
     fullest
    1.19
     point
    1.07
     extent
    1.05
     brim
    1.05
     tune
    1.04
     detriment
    1.04
     brink
    1.03
     utmost
    1.01
     marrow
    0.99
     limit
    0.95
    Activations Density 0.079%

    No Known Activations