© 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 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. 2-RES-JB
    11. 21895
    Prev
    Next
    INDEX
    Explanations

    images to enlarge with caption text

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific action or command related to enlarging or toggling images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ago
    -0.71
    comes
    -0.69
    stood
    -0.65
     awaited
    -0.64
     OC
    -0.62
     avail
    -0.62
     PS
    -0.62
    ild
    -0.62
    shall
    -0.61
     KING
    -0.61
    POSITIVE LOGITS
    Enlarge
    1.43
    Reviewer
    0.99
    toggle
    0.90
     "$:/
    0.88
    aukee
    0.82
     Thumbnails
    0.81
     toggle
    0.80
    pmwiki
    0.79
    ONSORED
    0.78
    hran
    0.77
    Activations Density 0.006%

    No Known Activations