© 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. 10-RES-JB
    11. 10071
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and the treatment of different groups in society

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social injustice and marginalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brewing
    -0.83
     Trails
    -0.75
     Cycling
    -0.71
    eton
    -0.68
     Website
    -0.67
     rollout
    -0.66
     Revival
    -0.65
    iasm
    -0.64
    chedel
    -0.64
     understatement
    -0.64
    POSITIVE LOGITS
     expend
    1.21
     unworthy
    1.19
     criminals
    1.15
     disposable
    1.14
     helpless
    1.12
     oppressed
    1.07
     pawn
    1.05
     deserving
    1.05
     sinners
    1.04
     equals
    1.02
    Activations Density 0.309%

    No Known Activations