© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10209
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or doubt

    oai_token-act-pair · gpt-3.5-turbo

    frequent use of the word "really" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifully
    -0.79
     nevertheless
    -0.79
    vic
    -0.76
    tein
    -0.76
     nonetheless
    -0.75
    moil
    -0.70
    iful
    -0.67
    enary
    -0.66
    VL
    -0.64
    ItemThumbnailImage
    -0.63
    POSITIVE LOGITS
     cared
    0.97
     bothered
    0.94
     mattered
    0.90
     bother
    0.82
     fit
    0.76
     understood
    0.75
    hin
    0.74
     bothering
    0.74
    FTWARE
    0.73
     anything
    0.71
    Activations Density 0.056%

    No Known Activations