© 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. 6211
    Prev
    Next
    INDEX
    Explanations

    specific groups of people based on characteristics or affiliations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to discrimination and targeted hate speech

    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
    staking
    -0.74
    thumbnails
    -0.74
    flex
    -0.73
    mares
    -0.69
    flows
    -0.69
    Alert
    -0.67
    blocks
    -0.67
    orders
    -0.65
    amar
    -0.65
    ulations
    -0.65
    POSITIVE LOGITS
     particular
    1.23
     person
    1.10
     specific
    1.08
     subset
    1.06
     individual
    1.05
     constituent
    1.00
     deity
    1.00
     entity
    0.97
     piece
    0.96
     perpetrator
    0.95
    Activations Density 0.431%

    No Known Activations