© 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. 4-RES-JB
    11. 12532
    Prev
    Next
    INDEX
    Explanations

    specific words related to the term "Fury" and geographic location mentions like "Fiji", as well as some specific names like "Gust" and "Vega"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific titles or notable entities

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

    No Comments

    Negative Logits
    pocket
    -0.83
    kai
    -0.77
    organic
    -0.77
    izational
    -0.76
    repeat
    -0.75
    emark
    -0.74
     quo
    -0.72
    ership
    -0.72
    ä¸ī
    -0.72
    opathy
    -0.71
    POSITIVE LOGITS
     Fury
    1.03
    anche
    0.83
    rites
    0.79
    ous
    0.73
    ricanes
    0.71
     Cutter
    0.70
    edIn
    0.69
    quit
    0.69
    burgh
    0.69
     Alley
    0.68
    Activations Density 0.016%

    No Known Activations