Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 5418
    Prev
    Next
    INDEX
    Explanations

    reports of catastrophic events resulting in casualties

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to casualties and injuries in various incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.96
    dayName
    -0.89
    paren
    -0.78
    SpaceEngineers
    -0.75
    natureconservancy
    -0.74
    arius
    -0.69
     ECO
    -0.69
    reality
    -0.69
    ivalry
    -0.69
    adian
    -0.67
    POSITIVE LOGITS
     wounded
    1.16
     wounding
    1.12
     injuring
    1.11
     injured
    1.09
     hospitalized
    1.05
     injure
    0.95
     killed
    0.85
     casualties
    0.83
     fatalities
    0.81
    jured
    0.80
    Activations Density 0.252%

    No Known Activations