© 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. 10-RES-JB
    11. 12184
    Prev
    Next
    INDEX
    Explanations

    descriptions related to negative societal issues or disasters

    oai_token-act-pair · gpt-3.5-turbo

    topics related to health crises and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    poke
    -0.66
    neutral
    -0.65
    topic
    -0.64
    ":"/
    -0.64
    vantage
    -0.63
    tarian
    -0.63
    ecided
    -0.63
    olitical
    -0.62
     complementary
    -0.62
    imum
    -0.62
    POSITIVE LOGITS
     unbearable
    1.12
     heartbreaking
    1.08
     untreated
    1.05
     staggering
    1.04
     starvation
    1.02
     crippling
    1.02
     appalling
    0.99
     indign
    0.98
     horrific
    0.98
     horrendous
    0.96
    Activations Density 1.259%

    No Known Activations