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

    Neuronpedia

    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. 23018
    Prev
    Next
    INDEX
    Explanations

    racial or gender disparities and comparisons in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to gender and racial disparities

    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
     IPM
    -0.66
     Nikki
    -0.65
     Canaver
    -0.63
     Ambro
    -0.60
     defect
    -0.58
     Carly
    -0.58
     resemb
    -0.56
    semb
    -0.56
    ascade
    -0.54
     Kear
    -0.53
    POSITIVE LOGITS
     counterparts
    0.95
    verages
    0.77
     peers
    0.69
     anymore
    0.68
    ifle
    0.67
    ensis
    0.66
    illac
    0.65
    aurus
    0.65
    eker
    0.65
    ecause
    0.64
    Activations Density 0.298%

    No Known Activations