© 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. 0-RES-JB
    11. 4907
    Prev
    Next
    INDEX
    Explanations

    the word "Pretty" used as an adjective in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "pretty" 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 @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wedge
    -0.74
     experienced
    -0.69
     sever
    -0.68
     sympath
    -0.68
     vent
    -0.67
     sanctioned
    -0.67
     assessment
    -0.63
     ventilation
    -0.63
     eject
    -0.63
     acceleration
    -0.62
    POSITIVE LOGITS
     Pretty
    3.37
    Pretty
    2.57
    pretty
    1.81
     Sounds
    1.30
     Totally
    1.29
     Lovely
    1.23
     Basically
    1.21
     Nice
    1.18
    Nice
    1.17
     Seems
    1.16
    Activations Density 0.034%

    No Known Activations