© 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. 6523
    Prev
    Next
    INDEX
    Explanations

    keywords related to various types of tools, services, and resources available for use in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts

    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
    umar
    -0.81
    lear
    -0.70
    Based
    -0.69
    hya
    -0.65
    oca
    -0.64
    itute
    -0.64
    ACTED
    -0.64
    kr
    -0.63
    href
    -0.63
    Ñı
    -0.63
    POSITIVE LOGITS
     assorted
    1.24
     others
    1.18
     other
    1.12
    etc
    1.11
     countless
    1.10
     etc
    1.07
     even
    1.07
     myriad
    1.06
     innumerable
    1.02
     many
    0.97
    Activations Density 0.274%

    No Known Activations