Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 1920
    Prev
    Next
    INDEX
    Explanations

    words related to dignity and respect

    oai_token-act-pair · gpt-3.5-turbo

    references to dignity and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     warning
    -0.67
    beam
    -0.64
    wine
    -0.63
    zig
    -0.61
    weight
    -0.61
     seeker
    -0.61
    market
    -0.59
     flared
    -0.57
     seeded
    -0.57
    manship
    -0.57
    POSITIVE LOGITS
    andum
    1.00
    itary
    0.93
    uchin
    0.87
    itous
    0.85
    itutional
    0.82
    antly
    0.82
    estones
    0.82
    arily
    0.81
    porary
    0.81
    ochond
    0.80
    Activations Density 0.073%

    No Known Activations