© 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. 18012
    Prev
    Next
    INDEX
    Explanations

    instances of mistreatment, discrimination, and abuse towards various groups of people

    oai_token-act-pair · gpt-3.5-turbo

    issues related to social injustice and discrimination against vulnerable groups

    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
    maxwell
    -0.68
     Extend
    -0.65
     Seller
    -0.65
     Prediction
    -0.62
    clinton
    -0.61
     Current
    -0.61
    cul
    -0.59
    mine
    -0.59
     Formation
    -0.58
     Sync
    -0.58
    POSITIVE LOGITS
     interrogated
    1.42
     punished
    1.32
     subjected
    1.29
     ridiculed
    1.25
     treated
    1.23
     rewarded
    1.20
     beaten
    1.20
     thrown
    1.17
     humiliated
    1.16
     harassed
    1.16
    Activations Density 0.410%

    No Known Activations