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. 17883
    Prev
    Next
    INDEX
    Explanations

    mentions of hurricanes

    oai_token-act-pair · gpt-3.5-turbo

    references to hurricanes

    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
     Bender
    -0.81
     Thieves
    -0.74
     Kafka
    -0.71
     Schiff
    -0.70
     Flex
    -0.68
     Rack
    -0.67
     Frey
    -0.67
     VAT
    -0.66
     Lust
    -0.65
     OCD
    -0.65
    POSITIVE LOGITS
    hur
    2.42
     hur
    2.19
    apeake
    1.76
    Hur
    1.70
    aer
    1.35
     Hurricanes
    1.33
    uras
    1.24
    alam
    1.18
     ampl
    1.09
    vir
    1.08
    Activations Density 0.056%

    No Known Activations