© 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. 8-RES-JB
    11. 20281
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal attributes or characteristics, such as gender, nationality, or physical appearance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gender identity and societal perceptions of gender

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trickle
    -0.80
     urgency
    -0.78
     patience
    -0.78
     distraction
    -0.76
     rush
    -0.76
     impat
    -0.72
     overload
    -0.72
     hurry
    -0.72
     optimization
    -0.72
     payoff
    -0.71
    POSITIVE LOGITS
     Therefore
    0.75
    Therefore
    0.75
     ancestry
    0.74
     nationality
    0.73
    Origin
    0.72
    properties
    0.71
    onyms
    0.70
     marrying
    0.70
     chromosomes
    0.69
     pronouns
    0.69
    Activations Density 0.922%

    No Known Activations