© 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. 10-RES-JB
    11. 9935
    Prev
    Next
    INDEX
    Explanations

    ethnicities or nationalities

    oai_token-act-pair · gpt-3.5-turbo

    ethnic and racial identity references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forcement
    -0.77
     VIDEOS
    -0.70
    pload
    -0.69
    initions
    -0.68
    MENTS
    -0.66
    livion
    -0.64
    ythm
    -0.63
    rocal
    -0.62
     subsequ
    -0.62
    agement
    -0.62
    POSITIVE LOGITS
     enough
    0.92
    enough
    0.88
    ethnic
    0.84
    ;
    0.81
     Caucasian
    0.81
     ancest
    0.81
     supremacist
    0.80
     born
    0.77
    listed
    0.77
     immigrant
    0.76
    Activations Density 0.156%

    No Known Activations