© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 3662
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences mentioning the basis of discrimination, especially related to factors like race, sex, sexual orientation, age, and arbitrary standards

    oai_token-act-pair · gpt-3.5-turbo

    references to grounds for discrimination in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uckland
    -0.72
     Unloaded
    -0.67
    ilet
    -0.65
    along
    -0.65
    hiba
    -0.65
    stall
    -0.65
    bats
    -0.64
    apore
    -0.63
    jam
    -0.63
    fried
    -0.63
    POSITIVE LOGITS
     behalf
    0.88
     principles
    0.83
     whim
    0.83
     ethnicity
    0.83
     sheer
    0.82
     nationality
    0.80
     virtue
    0.79
     differing
    0.78
     merit
    0.77
     quotas
    0.76
    Activations Density 0.176%

    No Known Activations