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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 18290
    Prev
    Next
    INDEX
    Explanations

    specific mentions of causes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causes of events or conditions

    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
    istas
    -0.80
    nets
    -0.77
    é¾įåĸļ士
    -0.71
    nis
    -0.70
    bags
    -0.69
    selves
    -0.69
    notations
    -0.69
     Marketable
    -0.67
    iaries
    -0.65
     Prosecutors
    -0.65
    POSITIVE LOGITS
     death
    1.17
     illness
    1.00
     blindness
    0.93
     homelessness
    0.92
     instability
    0.87
     sickness
    0.86
     stagnation
    0.85
     injury
    0.85
     mortality
    0.84
     occurrence
    0.82
    Activations Density 0.082%

    No Known Activations