© 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. 1-RES-JB
    11. 19987
    Prev
    Next
    INDEX
    Explanations

    words related to reversing decisions or judgments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "overturn" and its variations, reflecting themes of legal or societal change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.76
    Pros
    -0.74
    rug
    -0.70
    âĻ
    -0.70
    OTOS
    -0.69
    cca
    -0.68
    OST
    -0.67
    erenn
    -0.66
    ULT
    -0.66
    ART
    -0.65
    POSITIVE LOGITS
     overturn
    1.41
     overturned
    1.21
    hurst
    0.97
     revers
    0.87
     rewriting
    0.81
     reversed
    0.76
     flips
    0.76
    ĸļ
    0.75
     rewrite
    0.75
    strate
    0.74
    Activations Density 0.006%

    No Known Activations