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. 4-RES-JB
    6. 19018
    Prev
    Next
    INDEX
    Explanations

    terms related to LGBTQ community and rights

    oai_token-act-pair · gpt-3.5-turbo

    mentions of LGBTQ-related topics and issues

    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
     reper
    -0.67
     Rove
    -0.67
     respir
    -0.66
    nings
    -0.64
    acca
    -0.63
    osaurs
    -0.62
    ptin
    -0.62
     Luck
    -0.61
    pered
    -0.61
    igne
    -0.61
    POSITIVE LOGITS
    WER
    0.78
     LGBTQ
    0.77
    Leaks
    0.76
    LGBT
    0.76
    uably
    0.76
     Spectrum
    0.75
    ues
    0.75
    UE
    0.73
     spectrum
    0.72
    endered
    0.71
    Activations Density 0.006%

    No Known Activations