© 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. 17489
    Prev
    Next
    INDEX
    Explanations

    mentions of cakes

    oai_token-act-pair · gpt-3.5-turbo

    references to cakes

    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
     WATCHED
    -0.65
    audi
    -0.62
    igious
    -0.61
     Powers
    -0.60
    vernment
    -0.60
     neighbouring
    -0.60
     Lomb
    -0.58
    nesota
    -0.57
    tested
    -0.57
    unknown
    -0.57
    POSITIVE LOGITS
    cakes
    1.21
     cake
    1.18
    cake
    1.14
     cakes
    1.03
    ecake
    0.93
    meal
    0.93
     Cake
    0.88
    fruit
    0.82
    pillar
    0.79
    xual
    0.75
    Activations Density 0.010%

    No Known Activations