© 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. 3-RES-JB
    11. 15200
    Prev
    Next
    INDEX
    Explanations

    phrases related to increased risk of medical conditions or mortality

    oai_token-act-pair · gpt-3.5-turbo

    references to various health risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elf
    -0.78
     Seasons
    -0.75
    Nap
    -0.73
    Bit
    -0.72
    ilver
    -0.71
    TERN
    -0.69
    eve
    -0.68
     FANTASY
    -0.68
    zeb
    -0.67
    ION
    -0.67
    POSITIVE LOGITS
     risks
    0.93
     risk
    0.92
     proble
    0.84
     hazards
    0.83
    iest
    0.82
     horm
    0.82
     mortality
    0.81
     aversion
    0.79
    risk
    0.79
    taking
    0.78
    Activations Density 0.021%

    No Known Activations