© 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. 18491
    Prev
    Next
    INDEX
    Explanations

    mentions of a particular type of cheese - parmesan

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of cheese, especially vegan options

    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
    READ
    -0.65
     lockout
    -0.62
    LESS
    -0.61
    ICE
    -0.61
    FUL
    -0.61
     Presidents
    -0.60
     independence
    -0.60
    ALLY
    -0.58
     Governments
    -0.58
    California
    -0.56
    POSITIVE LOGITS
    mes
    1.19
    cript
    1.01
    bourg
    0.94
    hed
    0.93
    aurus
    0.90
    xual
    0.89
    cape
    0.85
    ovember
    0.85
    hew
    0.84
    quite
    0.81
    Activations Density 0.007%

    No Known Activations