© 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. 18553
    Prev
    Next
    INDEX
    Explanations

    phrases related to social justice and human rights advocacies

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups who are marginalized or discriminated against

    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
    ob
    -0.79
    OB
    -0.68
    opoly
    -0.67
    onis
    -0.67
     Serpent
    -0.64
    bang
    -0.64
    PB
    -0.62
     Hang
    -0.62
    ointment
    -0.61
    kamp
    -0.59
    POSITIVE LOGITS
     wishing
    1.01
     who
    0.98
     pesky
    0.88
    who
    0.82
     entrusted
    0.80
     kinds
    0.80
     favoring
    0.80
     affected
    0.80
     interested
    0.79
     interviewed
    0.79
    Activations Density 0.069%

    No Known Activations