© 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. 16752
    Prev
    Next
    INDEX
    Explanations

    phrases related to equality, community support, and societal welfare

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fairness and equality within community representation

    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
     pse
    -0.71
     unanim
    -0.70
     bluff
    -0.67
    oret
    -0.67
     Oops
    -0.66
     embry
    -0.65
    tein
    -0.65
    iban
    -0.64
     JPM
    -0.62
     disg
    -0.61
    POSITIVE LOGITS
     seamlessly
    0.73
    without
    0.71
     affordable
    0.70
    cult
    0.67
    HCR
    0.66
    Unique
    0.66
     unforgettable
    0.65
     accessible
    0.64
    .","
    0.63
    efined
    0.62
    Activations Density 0.905%

    No Known Activations