© 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. 10-RES-JB
    11. 20427
    Prev
    Next
    INDEX
    Explanations

    references to storms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of storms and weather-related phenomena

    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
    atem
    -0.89
    ibling
    -0.77
    atown
    -0.72
    olars
    -0.72
    buquerque
    -0.69
     Parenthood
    -0.68
    ADRA
    -0.67
    cius
    -0.66
    ¿½
    -0.66
    ately
    -0.66
    POSITIVE LOGITS
    tro
    1.66
    cloud
    1.05
    water
    1.04
    storm
    1.02
     troopers
    1.01
    front
    1.00
     trooper
    0.99
    storms
    0.99
    shield
    0.98
     clouds
    0.94
    Activations Density 0.030%

    No Known Activations