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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 2431
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "whiteness"

    oai_token-act-pair · gpt-3.5-turbo

    references to race, particularly regarding whiteness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Population
    -0.80
    UTION
    -0.78
    Reference
    -0.78
    VID
    -0.75
    raltar
    -0.73
     GEAR
    -0.68
    Technical
    -0.67
    GAN
    -0.67
    GS
    -0.67
    Term
    -0.67
    POSITIVE LOGITS
    ewater
    1.11
     whit
    1.09
    elist
    0.95
    eness
    0.93
    ening
    0.89
    ened
    0.88
    etooth
    0.79
    eless
    0.79
    ipedia
    0.77
    iless
    0.76
    Activations Density 0.008%

    No Known Activations