© 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. 8-RES-JB
    11. 9472
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the concept of impossibility

    oai_token-act-pair · gpt-3.5-turbo

    statements about things that are deemed impossible

    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
    oola
    -0.86
    lique
    -0.80
    aina
    -0.79
    notations
    -0.74
    avia
    -0.74
    osi
    -0.73
    ingle
    -0.72
    notation
    -0.72
    rika
    -0.72
    ivities
    -0.72
    POSITIVE LOGITS
     feas
    0.79
     conceivable
    0.71
     foreseeable
    0.66
    ĵĺ
    0.66
     dreamed
    0.66
     imaginable
    0.65
     muster
    0.65
     unanim
    0.64
     feat
    0.64
    ossible
    0.64
    Activations Density 0.039%

    No Known Activations