© 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. 3-RES-JB
    11. 1855
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sesame"

    oai_token-act-pair · gpt-3.5-turbo

    references to sesame as well as the names of specific locations and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prosecut
    -0.68
     Heller
    -0.66
     FML
    -0.65
    ossier
    -0.65
     newsp
    -0.61
    desktop
    -0.59
     heaviest
    -0.59
    nant
    -0.58
     respons
    -0.58
     skelet
    -0.58
    POSITIVE LOGITS
    esame
    1.00
    bean
    0.87
    opard
    0.86
    ousy
    0.83
    seed
    0.83
    ira
    0.79
    outh
    0.78
    anut
    0.77
    vous
    0.76
    anuts
    0.75
    Activations Density 0.009%

    No Known Activations