© 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. 15161
    Prev
    Next
    INDEX
    Explanations

    mentions of experiences, events, or conditions that have occurred or been observed

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "experienced" and other related terms indicating change or significant events

    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
    theless
    -0.75
     entit
    -0.72
     Laboratories
    -0.69
     answ
    -0.66
    tein
    -0.63
    POSE
    -0.63
    LES
    -0.60
    PLIED
    -0.60
    PLA
    -0.59
    çĦ
    -0.59
    POSITIVE LOGITS
     brunt
    1.04
     seismic
    0.84
     Hurricane
    0.84
    inventoryQuantity
    0.82
     massive
    0.82
     upheaval
    0.81
     influx
    0.81
     earthquakes
    0.80
     layoffs
    0.80
     losses
    0.79
    Activations Density 0.313%

    No Known Activations