© 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. 12-RES-JB
    11. 3918
    Prev
    Next
    INDEX
    Explanations

    specific categories or options within a larger context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    elements related to options and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    attled
    -0.68
    isible
    -0.66
    erenn
    -0.62
    starting
    -0.62
    fine
    -0.61
     unwilling
    -0.61
    geoning
    -0.60
    00007
    -0.60
     exting
    -0.59
    ushing
    -0.59
    POSITIVE LOGITS
     they
    0.80
     you
    0.75
    soever
    0.75
     constitutes
    0.70
    yip
    0.69
     THEY
    0.69
     corresponds
    0.66
     dominates
    0.65
     existed
    0.65
     qualifies
    0.64
    Activations Density 0.178%

    No Known Activations