© 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. 2-RES-JB
    11. 20918
    Prev
    Next
    INDEX
    Explanations

    references to meteorological or natural atmospheric phenomena, specifically clouds

    oai_token-act-pair · gpt-3.5-turbo

    references to clouds in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.95
    IGN
    -0.82
    TI
    -0.78
    Labor
    -0.75
    AE
    -0.73
    Du
    -0.73
    Sem
    -0.72
    Union
    -0.71
    Else
    -0.71
    MIT
    -0.70
    POSITIVE LOGITS
     clouds
    1.25
    burst
    1.15
     Clouds
    0.99
     cloud
    0.99
    bows
    0.89
     flakes
    0.86
     puff
    0.85
     drifting
    0.83
     swirling
    0.83
     blowing
    0.82
    Activations Density 0.008%

    No Known Activations