© 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. 11-RES-JB
    11. 2462
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inclusivity or disregard of specific conditions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing inclusivity and the concept of equality regardless of various classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BSD
    -0.79
    ©¶æ¥µ
    -0.78
    together
    -0.70
    very
    -0.69
    Hyd
    -0.69
    HEAD
    -0.69
    birds
    -0.68
    ãĥ¥
    -0.68
    bably
    -0.68
    Micro
    -0.68
    POSITIVE LOGITS
     circumstance
    1.22
     whether
    1.22
     nationality
    1.12
     denomination
    1.05
     affiliation
    1.02
     ethnicity
    1.00
     geography
    1.00
     circumstances
    0.99
     creed
    0.97
     origin
    0.95
    Activations Density 0.053%

    No Known Activations