© 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. 13265
    Prev
    Next
    INDEX
    Explanations

    references to press conferences and sports-related events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of scheduled events and practice sessions in a formal context

    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
    £
    -0.71
    Quantity
    -0.70
    wark
    -0.66
    alogue
    -0.64
    anmar
    -0.64
    apest
    -0.64
    chin
    -0.63
     quantity
    -0.61
    $,
    -0.61
     Despair
    -0.59
    POSITIVE LOGITS
     locker
    1.47
     scrimmage
    1.34
     offseason
    1.28
     workouts
    1.28
     halftime
    1.22
     workout
    1.21
     practice
    1.20
    practice
    1.19
     clubhouse
    1.18
     practices
    1.17
    Activations Density 0.403%

    No Known Activations