© 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. 2761
    Prev
    Next
    INDEX
    Explanations

    information or statements indicating ease of comprehension or availability

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

    phrases indicating ease of access or usability

    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
     Farmers
    -0.74
     strongly
    -0.71
    Merit
    -0.71
    yet
    -0.70
    ently
    -0.68
     strictly
    -0.68
    IAL
    -0.68
    initely
    -0.68
    Strong
    -0.66
    mostly
    -0.65
    POSITIVE LOGITS
     identifiable
    1.19
     recognizable
    0.99
     accessible
    0.97
     convertible
    0.92
     distinguish
    0.92
     digest
    0.91
     achievable
    0.91
    accessible
    0.89
     overlooked
    0.88
     removable
    0.88
    Activations Density 0.063%

    No Known Activations