© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3555
    Prev
    Next
    INDEX
    Explanations

    conjunctions 'whether' or 'or'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "whether or not."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hilton
    -0.73
     Dragonbound
    -0.67
     Pony
    -0.63
     Cardinal
    -0.63
     Shinra
    -0.63
    ://
    -0.60
     Trophy
    -0.60
     Lover
    -0.60
     Hew
    -0.58
     Chau
    -0.58
    POSITIVE LOGITS
    Else
    1.08
    acles
    1.00
    acle
    0.94
     else
    0.84
    rame
    0.73
    chard
    0.72
    nam
    0.70
    acl
    0.70
    leans
    0.69
    romeda
    0.69
    Activations Density 0.022%

    No Known Activations