© 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. 3319
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating significant events, victories, or actions that have an impact on a larger community or group

    oai_token-act-pair · gpt-3.5-turbo

    prominent articles preceding important milestones or significant events

    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
    sheets
    -0.81
    rates
    -0.75
    iencies
    -0.73
    existence
    -0.71
    izons
    -0.70
    groups
    -0.68
    organisms
    -0.68
    iterator
    -0.68
    bags
    -0.67
    arth
    -0.67
    POSITIVE LOGITS
     watershed
    1.32
     setback
    1.26
     milestone
    1.24
     landmark
    1.20
     blow
    1.14
     harb
    1.14
     victory
    1.11
     rebuke
    1.10
     reminder
    1.10
     bombshell
    1.07
    Activations Density 0.221%

    No Known Activations