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. 6-RES-JB
    6. 14383
    Prev
    Next
    INDEX
    Explanations

    characteristics related to demographics such as age, race, sex, and income

    oai_token-act-pair · gpt-3.5-turbo

    demographical factors such as age, sex, race, and ethnicity

    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
    olars
    -0.80
    cour
    -0.80
    cit
    -0.77
    inka
    -0.74
    mud
    -0.74
    ossus
    -0.74
    etsk
    -0.72
    roo
    -0.72
    BLIC
    -0.70
    olin
    -0.70
    POSITIVE LOGITS
     specific
    0.93
     affiliation
    0.92
     nationality
    0.85
     preferences
    0.84
     differences
    0.84
     ethnicity
    0.83
     severity
    0.81
     angle
    0.80
     quantity
    0.80
     specifics
    0.79
    Activations Density 0.512%

    No Known Activations