© 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. 8-RES-JB
    11. 1171
    Prev
    Next
    INDEX
    Explanations

    phrases related to ability and improvement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of capability or action, particularly those involving the phrase "can do."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mes
    -0.62
    Lenin
    -0.62
     Kub
    -0.59
    awar
    -0.58
    doms
    -0.57
    IL
    -0.57
     Related
    -0.56
    uggest
    -0.56
    BuyableInstoreAndOnline
    -0.56
    bush
    -0.55
    POSITIVE LOGITS
     easily
    1.07
     safely
    1.05
     freely
    0.91
     cheaply
    0.88
     comfortably
    0.82
    ibly
    0.80
     afford
    0.77
     feas
    0.76
    ivably
    0.76
     confidently
    0.75
    Activations Density 0.341%

    No Known Activations