© 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. 13875
    Prev
    Next
    INDEX
    Explanations

    contractions where 'not' is followed by a word

    oai_token-act-pair · gpt-3.5-turbo

    the word "shouldn't" and its variations, indicating expressions of advisement or critique

    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
     enthusi
    -0.80
     Powered
    -0.70
     locating
    -0.69
     withd
    -0.68
     encount
    -0.68
     gobl
    -0.66
     paran
    -0.63
     Herz
    -0.63
     fulfilled
    -0.62
     bombed
    -0.62
    POSITIVE LOGITS
    't
    1.58
    ned
    1.00
    n
    1.00
    ny
    0.99
    ighed
    0.90
    nt
    0.88
    ÃŃ
    0.86
    no
    0.83
    ouch
    0.82
    ning
    0.81
    Activations Density 0.017%

    No Known Activations