© 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. 20764
    Prev
    Next
    INDEX
    Explanations

    words related to abolishment or removal

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of abolition and the act of abolishing various practices or laws

    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
     Fault
    -0.73
     Emin
    -0.69
     Io
    -0.65
    MAT
    -0.65
    PAR
    -0.64
     Gaia
    -0.64
     Furious
    -0.63
     Cascade
    -0.63
     Pug
    -0.62
    Gro
    -0.61
    POSITIVE LOGITS
     abolish
    1.32
     abolition
    1.24
     abolished
    1.19
     abol
    1.15
    ©¶æ¥µ
    1.05
    ishment
    0.87
    hyde
    0.85
    ĸļ
    0.84
     decriminal
    0.82
     slavery
    0.79
    Activations Density 0.010%

    No Known Activations