© 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. 8990
    Prev
    Next
    INDEX
    Explanations

    inflammatory sentences or negative events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe a situation or state, often beginning with "It's a."

    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
    units
    -0.85
    Versions
    -0.84
    notes
    -0.82
    agues
    -0.78
    Orig
    -0.75
    DOM
    -0.74
    Edit
    -0.74
    onduct
    -0.73
    TPS
    -0.73
    reports
    -0.72
    POSITIVE LOGITS
     fascinating
    1.14
     coincidence
    1.11
     reminder
    1.05
     pity
    1.04
     lot
    0.99
     daunting
    0.98
     simple
    0.98
     bit
    0.95
     nice
    0.94
     testament
    0.94
    Activations Density 0.163%

    No Known Activations