© 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. 9-RES-JB
    11. 1011
    Prev
    Next
    INDEX
    Explanations

    phrases referring to demographic attributes such as race, ethnicity, and gender

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing racial and gender identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.80
     externalToEVAOnly
    -0.72
    iquid
    -0.71
     needles
    -0.67
     VIDEOS
    -0.67
    hyde
    -0.66
     livest
    -0.66
    netflix
    -0.65
    plementation
    -0.65
    downs
    -0.64
    POSITIVE LOGITS
     course
    0.98
     whom
    0.96
     Colour
    0.95
     stature
    0.93
     colour
    0.90
     varying
    0.89
    course
    0.87
     color
    0.83
     renown
    0.82
    sted
    0.81
    Activations Density 0.096%

    No Known Activations