© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12726
    Prev
    Next
    INDEX
    Explanations

    terms related to the environment, specifically bush and forest-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to "bush" and its related contexts, along with occasional mentions of "womb" and "foss."

    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
     Hamburg
    -0.67
    ructose
    -0.67
    Else
    -0.66
    earable
    -0.64
    ications
    -0.63
     insidious
    -0.63
    cussion
    -0.63
    */(
    -0.62
    oppable
    -0.62
    oric
    -0.61
    POSITIVE LOGITS
    fires
    1.10
     bush
    1.04
    craft
    1.03
    wh
    0.90
    fire
    0.88
    meat
    0.87
    tree
    0.87
    mere
    0.86
    ido
    0.82
    pole
    0.80
    Activations Density 0.006%

    No Known Activations