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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 12938
    Prev
    Next
    INDEX
    Explanations

    terms related to diversity, inclusion, and equality, particularly in the context of various identities and fields of work

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social justice and equality issues, particularly concerning marginalized communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pler
    -0.78
    è¦ļéĨĴ
    -0.72
    uces
    -0.67
    arin
    -0.64
    uthor
    -0.63
    ynthesis
    -0.62
    ETHOD
    -0.60
    peak
    -0.58
    agame
    -0.58
    oaded
    -0.58
    POSITIVE LOGITS
    etc
    1.14
     etc
    0.84
    whatever
    0.76
    â̦)
    0.70
     Transgender
    0.69
    sea
    0.63
    ospace
    0.62
    AppData
    0.61
     usb
    0.59
     united
    0.59
    Activations Density 0.238%

    No Known Activations