© 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. 1499
    Prev
    Next
    INDEX
    Explanations

    phrases related to health, safety, and societal impacts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to environmental and health-related impacts

    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
     quart
    -0.75
    ãĤ¦ãĤ¹
    -0.69
     Reserved
    -0.64
    odiac
    -0.63
    tick
    -0.62
     brill
    -0.62
    lord
    -0.60
    Ĭ
    -0.60
    icol
    -0.60
    blank
    -0.58
    POSITIVE LOGITS
     strengthen
    0.95
     improve
    0.92
     promote
    0.88
     improving
    0.88
     enhance
    0.85
     intensify
    0.85
     including
    0.84
     deepen
    0.82
     educate
    0.81
     particularly
    0.78
    Activations Density 0.307%

    No Known Activations