© 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. 0-RES-JB
    11. 4081
    Prev
    Next
    INDEX
    Explanations

    weather-related terms, particularly focusing on storms

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of storms

    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
     genital
    -0.76
     Hindi
    -0.73
     anus
    -0.66
     thumbs
    -0.66
     nominal
    -0.65
     vegetarian
    -0.65
     clitor
    -0.64
     anal
    -0.63
     comparative
    -0.63
     Bates
    -0.63
    POSITIVE LOGITS
    storm
    4.32
    storms
    3.27
    Storm
    2.12
     storm
    1.93
     storms
    1.61
     Storm
    1.46
    cloud
    1.25
    burst
    1.24
    wave
    1.21
    hur
    1.19
    Activations Density 0.013%

    No Known Activations