© 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 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. 9-RES-JB
    11. 1909
    Prev
    Next
    INDEX
    Explanations

    instances where a statement involves the concept of ability or potential

    oai_token-act-pair · gpt-3.5-turbo

    conditional and potential actions or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.78
     Continued
    -0.72
     whenever
    -0.63
    ients
    -0.63
     wherever
    -0.61
     LOT
    -0.60
     snipp
    -0.60
     Lis
    -0.58
     direction
    -0.57
     boiler
    -0.57
    POSITIVE LOGITS
     afford
    1.09
     boast
    1.01
     survive
    1.01
     justify
    1.00
     conceive
    0.99
     qualify
    0.96
     withstand
    0.96
     muster
    0.94
     attest
    0.93
     convince
    0.91
    Activations Density 0.145%

    No Known Activations