© 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. 6-RES-JB
    11. 9661
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty about future outcomes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to be."

    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
    hops
    -0.65
     Advertisement
    -0.59
     hamm
    -0.59
     nets
    -0.56
     simultane
    -0.56
     jails
    -0.54
    pointers
    -0.54
     Boots
    -0.53
     suspended
    -0.53
     banned
    -0.52
    POSITIVE LOGITS
    ggles
    0.98
    asty
    0.94
    othy
    0.86
    pless
    0.85
    psy
    0.83
    ads
    0.76
    fu
    0.75
    asted
    0.74
    lling
    0.74
    adies
    0.73
    Activations Density 0.312%

    No Known Activations