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. 10-RES-JB
    6. 11674
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to discussing opinions and characteristics of groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to societal perceptions and stereotypes about various groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     looph
    -0.69
    ework
    -0.65
    Stretch
    -0.64
    Torrent
    -0.63
     maneu
    -0.63
    vere
    -0.63
     withdrew
    -0.63
     defied
    -0.60
     Banner
    -0.60
    annis
    -0.60
    POSITIVE LOGITS
     invariably
    1.39
     usually
    1.04
     inevitably
    0.99
     cringe
    0.98
    often
    0.93
    usually
    0.91
     referring
    0.90
     typically
    0.87
     reply
    0.86
    rase
    0.83
    Activations Density 0.350%

    No Known Activations