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. 0-RES-JB
    6. 23436
    Prev
    Next
    INDEX
    Explanations

    the word "hail" or related variations

    oai_token-act-pair · gpt-3.5-turbo

    references to hail and fallout in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tate
    -0.78
     refresh
    -0.71
    Nut
    -0.70
    chest
    -0.69
     Processor
    -0.69
     Avatar
    -0.67
    oise
    -0.67
    Pinterest
    -0.66
    erer
    -0.65
     Kraken
    -0.65
    POSITIVE LOGITS
     hail
    2.46
     hailed
    2.00
    vind
    1.53
    iren
    1.48
     Hail
    1.25
     fallout
    1.23
     Shinzo
    0.96
    irens
    0.94
     landslide
    0.94
     Tayyip
    0.92
    Activations Density 0.049%

    No Known Activations