© 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. 11-RES-JB
    11. 6231
    Prev
    Next
    INDEX
    Explanations

    phrases related to failure or the inability to achieve a desired outcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating failure or inability to achieve something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Flo
    -0.79
    soDeliveryDate
    -0.77
    WER
    -0.68
    EStream
    -0.68
    calling
    -0.65
    DragonMagazine
    -0.65
    Sold
    -0.64
     Cutter
    -0.63
    Fra
    -0.63
    Textures
    -0.61
    POSITIVE LOGITS
     disclose
    1.23
     capitalize
    1.21
     adequately
    1.20
     heed
    1.18
     comply
    1.17
     grasp
    1.17
     fulfill
    1.15
     adhere
    1.12
     anticipate
    1.11
     convince
    1.10
    Activations Density 0.073%

    No Known Activations