© 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. 0-RES-JB
    11. 21511
    Prev
    Next
    INDEX
    Explanations

    words related to multiracial identity and demographics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to racial and ethnic categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     messenger
    -0.71
     Vend
    -0.66
     Lloyd
    -0.64
     ops
    -0.63
     dir
    -0.62
     Boll
    -0.61
     mun
    -0.61
     Wright
    -0.60
     Dill
    -0.59
     quotes
    -0.59
    POSITIVE LOGITS
    acial
    4.70
    acist
    1.53
    aces
    1.18
    acists
    1.18
    icial
    1.11
    racial
    1.06
    rontal
    1.05
    atown
    1.04
    ictional
    1.02
    atial
    1.00
    Activations Density 0.014%

    No Known Activations