© 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. 318
    Prev
    Next
    INDEX
    Explanations

    mentions of someone dying at a specific location

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "at," particularly in contexts relating to locations or 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
    View
    -0.70
    podcast
    -0.70
     benefited
    -0.67
     thri
    -0.67
    hops
    -0.66
    LED
    -0.66
    DVD
    -0.64
    Prof
    -0.64
    Owner
    -0.63
    Pac
    -0.61
    POSITIVE LOGITS
     least
    1.15
    onement
    1.02
     halftime
    0.99
    rial
    0.98
    oning
    0.91
     midday
    0.90
     midnight
    0.88
    oned
    0.80
    yp
    0.80
    abase
    0.78
    Activations Density 0.174%

    No Known Activations