© 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. 6411
    Prev
    Next
    INDEX
    Explanations

    compound words formed by combining two separate words, with an emphasis on the second word

    oai_token-act-pair · gpt-3.5-turbo

    forms of prefixes or suffixes in relation to various words

    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
     interfaces
    -1.08
     fixtures
    -1.08
     offices
    -1.03
     establishments
    -1.02
     timelines
    -1.02
     resolutions
    -1.01
     associations
    -1.01
     channels
    -1.01
     commissions
    -0.98
     workplaces
    -0.98
    POSITIVE LOGITS
    ificant
    1.04
    ailable
    1.00
    illion
    1.00
    uristic
    0.99
    ordinate
    0.96
    ussian
    0.95
    igmatic
    0.95
    asket
    0.94
    ighter
    0.93
    risome
    0.93
    Activations Density 0.377%

    No Known Activations