© 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. 11260
    Prev
    Next
    INDEX
    Explanations

    synonyms or alternatives using the word 'or'

    oai_token-act-pair · gpt-3.5-turbo

    the word "or" used in a variety of 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
    Here
    -0.61
    Now
    -0.59
    erest
    -0.58
    NOW
    -0.58
    ires
    -0.58
    Therefore
    -0.58
     THEN
    -0.57
    hes
    -0.57
    LR
    -0.57
    Each
    -0.55
    POSITIVE LOGITS
    acle
    1.63
    nam
    1.59
    ifice
    1.56
    acles
    1.47
    chard
    1.42
    chid
    1.40
    acular
    1.28
    Else
    1.28
    atory
    1.20
    ific
    1.18
    Activations Density 0.131%

    No Known Activations