© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18436
    Prev
    Next
    INDEX
    Explanations

    contractions of 'is' and 'not'

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating the absence of something

    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
     PU
    -0.70
     Mechdragon
    -0.70
     dust
    -0.69
     mark
    -0.66
     couch
    -0.65
     flies
    -0.63
     retard
    -0.62
     compliment
    -0.62
     complete
    -0.62
     nearest
    -0.61
    POSITIVE LOGITS
    't
    1.57
    iting
    1.05
    ÃŃ
    1.04
    ited
    1.03
    itely
    1.01
    uts
    0.96
    eness
    0.95
    cest
    0.94
    its
    0.93
    atically
    0.92
    Activations Density 0.105%

    No Known Activations