© 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. 4-RES-JB
    11. 22484
    Prev
    Next
    INDEX
    Explanations

    words with the prefix "unf-" indicating negation or reversal

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "un" indicating negation or lack

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

    No Comments

    Negative Logits
    uyomi
    -1.01
    anwhile
    -0.96
    姫
    -0.89
    hyde
    -0.89
     Nanto
    -0.76
     Thornton
    -0.70
    piece
    -0.68
    wark
    -0.68
     Tackle
    -0.67
     Dynamics
    -0.67
    POSITIVE LOGITS
    athom
    1.13
    avour
    1.12
    riend
    1.06
    ortun
    1.01
    ortunately
    0.99
    requ
    0.98
    ruit
    0.97
    ixed
    0.96
    ishable
    0.96
    itt
    0.93
    Activations Density 0.003%

    No Known Activations