© 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. 8-RES-JB
    11. 1296
    Prev
    Next
    INDEX
    Explanations

    names of famous pop culture figures or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to specific musical artists and cultural entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •single token firings
    Fires on capitalized adjectives " Mighty", " Grateful", " Lucky", etc

    No Comments

    Negative Logits
    itals
    -0.86
    lished
    -0.84
    lessly
    -0.83
    ital
    -0.81
    merce
    -0.81
    itism
    -0.79
    haps
    -0.78
    orously
    -0.77
    ificial
    -0.77
    istically
    -0.76
    POSITIVE LOGITS
     Wings
    1.06
     Hearts
    1.05
     Ducks
    0.98
     Feet
    0.96
     Ones
    0.95
     Bears
    0.92
     Birds
    0.86
     Hands
    0.86
     Bones
    0.86
     Duck
    0.86
    Activations Density 0.148%

    No Known Activations