© 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. 5536
    Prev
    Next
    INDEX
    Explanations

    adjectives associated with speed or fast actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quick" and its associated variations

    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
    ationally
    -0.80
    #$#$
    -0.69
    ucc
    -0.65
    midt
    -0.62
    yond
    -0.62
     Province
    -0.61
     Marketable
    -0.60
    ational
    -0.58
     peacefully
    -0.57
    Haunted
    -0.57
    POSITIVE LOGITS
    lime
    1.18
    ened
    1.12
    ening
    1.10
    fix
    1.09
     succession
    1.07
    fixes
    1.07
     turnaround
    1.05
    draw
    1.01
    idious
    0.99
     fixes
    0.98
    Activations Density 0.063%

    No Known Activations