© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 6473
    Prev
    Next
    INDEX
    Explanations

    phrases describing the ease or difficulty of tasks

    oai_token-act-pair · gpt-3.5-turbo

    statements of existence or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     throats
    -0.78
    dylib
    -0.77
     rul
    -0.70
    luaj
    -0.70
     sockets
    -0.66
    ãĤ£
    -0.64
    rower
    -0.64
     ensu
    -0.62
     Peb
    -0.62
     inhabit
    -0.61
    POSITIVE LOGITS
     akin
    1.13
     pointless
    1.06
     futile
    1.06
     impossible
    1.05
     risky
    1.05
     counterproductive
    1.04
     easier
    1.03
     fraught
    1.02
     advisable
    1.02
     preferable
    0.98
    Activations Density 0.134%

    No Known Activations