© 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. 7-RES-JB
    11. 22943
    Prev
    Next
    INDEX
    Explanations

    conjunctions "or" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "or."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ires
    -0.73
    estamp
    -0.63
    ourn
    -0.61
    irlf
    -0.61
    ublic
    -0.59
    idem
    -0.57
    ascus
    -0.57
     Wast
    -0.57
    irms
    -0.57
    ights
    -0.56
    POSITIVE LOGITS
    ifice
    1.35
    Else
    1.31
    acles
    1.27
    acle
    1.25
    acular
    1.14
    chard
    1.10
    chid
    1.08
    nery
    1.04
     alternatively
    1.02
    ific
    1.00
    Activations Density 0.192%

    No Known Activations