© 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. 11-RES-JB
    11. 907
    Prev
    Next
    INDEX
    Explanations

    the word "or" followed by a numeric value

    oai_token-act-pair · gpt-3.5-turbo

    the word "or" and its variants 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 @ 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
    tackle
    -0.65
    ires
    -0.65
    estro
    -0.65
    Dom
    -0.63
    arten
    -0.62
    "}],"
    -0.61
    erd
    -0.61
    Date
    -0.61
    orn
    -0.61
    Ball
    -0.61
    POSITIVE LOGITS
     alternatively
    1.32
     rather
    1.10
     perhaps
    1.09
     worse
    1.06
     indeed
    1.05
     maybe
    1.05
     equival
    1.04
     whatever
    1.01
     lack
    0.99
     else
    0.98
    Activations Density 0.092%

    No Known Activations