© 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. 6783
    Prev
    Next
    INDEX
    Explanations

    phrases related to showcasing or demonstrating talent or skill

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shown" and its variations indicating talent or potential

    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
    76561
    -0.87
    oldown
    -0.76
    alez
    -0.73
    miah
    -0.71
    undo
    -0.70
    ksh
    -0.68
    osate
    -0.67
    merce
    -0.67
    idays
    -0.66
    pton
    -0.65
    POSITIVE LOGITS
     signs
    1.32
     promise
    1.20
     willingness
    1.15
     flashes
    1.10
     glimps
    1.08
    ered
    1.07
     reluctance
    1.01
     resilience
    0.99
     composure
    0.95
     remarkable
    0.95
    Activations Density 0.073%

    No Known Activations