© 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. 11-RES-JB
    11. 14864
    Prev
    Next
    INDEX
    Explanations

    official websites and events

    oai_token-act-pair · gpt-3.5-turbo

    references to official websites or pages associated with specific entities or events

    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
    theless
    -0.87
    etheless
    -0.83
     reconc
    -0.72
    staking
    -0.71
    ancial
    -0.70
     ourselves
    -0.69
    anwhile
    -0.69
     eleph
    -0.68
     whichever
    -0.64
     shifting
    -0.63
    POSITIVE LOGITS
     TBD
    0.80
    Beta
    0.76
     TBA
    0.75
    Jr
    0.71
    ml
    0.69
     Deluxe
    0.69
    Runner
    0.68
    Dex
    0.68
     Minion
    0.67
    Desktop
    0.67
    Activations Density 0.224%

    No Known Activations