© 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. 1246
    Prev
    Next
    INDEX
    Explanations

    words related to weather phenomena, specifically fog

    oai_token-act-pair · gpt-3.5-turbo

    references to "fog" as a metaphor for confusion or lack of clarity

    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
    vier
    -0.81
     Clement
    -0.80
    heit
    -0.78
     Perkins
    -0.76
     reciproc
    -0.76
     Trudeau
    -0.73
     Sinclair
    -0.72
    hops
    -0.72
    Char
    -0.71
    udeau
    -0.70
    POSITIVE LOGITS
     fog
    2.51
     VM
    1.42
     DR
    1.35
     Fog
    1.32
     haze
    1.25
     diagram
    1.16
     firewall
    1.10
     Frankfurt
    0.95
     clutter
    0.87
     bog
    0.86
    Activations Density 0.031%

    No Known Activations