© 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. 1-RES-JB
    11. 15933
    Prev
    Next
    INDEX
    Explanations

    phrases related to being overwhelmed or going crazy

    oai_token-act-pair · gpt-3.5-turbo

    references to "nuts" in various contexts, including food and emotional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pless
    -0.68
    oping
    -0.64
    Rate
    -0.63
    Reply
    -0.63
    ienced
    -0.62
    RAW
    -0.60
    Untitled
    -0.60
    lon
    -0.60
    VO
    -0.60
    ribute
    -0.60
    POSITIVE LOGITS
     nuts
    1.34
     peanuts
    0.98
    ħĭ
    0.95
    nuts
    0.94
    mith
    0.92
    terday
    0.87
     nut
    0.81
    hots
    0.77
     apples
    0.77
     bananas
    0.75
    Activations Density 0.007%

    No Known Activations