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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21445
    Prev
    Next
    INDEX
    Explanations

    words related to stigmatization and shame

    oai_token-act-pair · gpt-3.5-turbo

    references to stigma and its impact on individuals and communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.86
    irgin
    -0.84
    apeake
    -0.80
     pickups
    -0.77
    hire
    -0.73
    gd
    -0.67
    éĹĺ
    -0.67
    tes
    -0.66
    yrim
    -0.65
    ersive
    -0.65
    POSITIVE LOGITS
     stigma
    1.03
     stigmat
    0.93
    imaru
    0.77
     prejudice
    0.76
     prejud
    0.68
     Shame
    0.66
     Hai
    0.66
    pport
    0.65
     Tend
    0.65
     attached
    0.64
    Activations Density 0.030%

    No Known Activations