© 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 EvalsExportsinterp-engineNEWAPI 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. 21188
    Prev
    Next
    INDEX
    Explanations

    phrases related to remaining or ensuring correctness in technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to stability and consistency in data or processes

    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
    anship
    -0.76
    utical
    -0.74
    lihood
    -0.71
    vernment
    -0.69
    stakes
    -0.69
    utic
    -0.68
    seeking
    -0.67
     Opportunity
    -0.67
     Flavoring
    -0.65
    rouse
    -0.65
    POSITIVE LOGITS
     readable
    1.23
     identical
    1.14
     sorted
    1.13
     grouped
    1.08
     intact
    1.07
     interchangeable
    1.06
     synchronized
    1.06
     cached
    1.05
     unchanged
    1.04
     aligned
    1.03
    Activations Density 0.288%

    No Known Activations