© 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. 10109
    Prev
    Next
    INDEX
    Explanations

    terms related to drafts or versions of documents

    oai_token-act-pair · gpt-3.5-turbo

    references to drafts, prototypes, and averages related to various subjects

    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
    brids
    -0.98
    tics
    -0.95
    IGHTS
    -0.94
    renches
    -0.91
    anders
    -0.90
    ravings
    -0.87
    shirts
    -0.87
    ceans
    -0.86
    ombies
    -0.86
    bits
    -0.86
    POSITIVE LOGITS
     version
    1.01
     of
    0.91
     solution
    0.88
     arrangement
    0.87
     situation
    0.85
     thereof
    0.85
     implementation
    0.84
     environment
    0.84
     iteration
    0.83
     handshake
    0.83
    Activations Density 0.380%

    No Known Activations