© 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. 17827
    Prev
    Next
    INDEX
    Explanations

    terms related to segregation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to segregation and segregated populations

    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
    debian
    -0.69
    ulz
    -0.69
    OD
    -0.69
    rolog
    -0.65
    sonian
    -0.65
    nil
    -0.65
    kos
    -0.63
    thens
    -0.62
    thus
    -0.61
    td
    -0.61
    POSITIVE LOGITS
    gregation
    1.45
     segregation
    1.24
     segreg
    1.13
     segregated
    1.10
    pling
    0.94
    pees
    0.84
     apartheid
    0.79
    regation
    0.79
    greg
    0.79
    ipation
    0.78
    Activations Density 0.008%

    No Known Activations