© 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. 4-RES-JB
    11. 17305
    Prev
    Next
    INDEX
    Explanations

    words related to a specific event or place, "Maaret"

    oai_token-act-pair · gpt-3.5-turbo

    words related to rituals or performances, particularly in reference to rehearsals and events

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

    No Comments

    Negative Logits
    iphany
    -0.86
    ulner
    -0.81
    uador
    -0.80
    umar
    -0.74
    abul
    -0.73
    sen
    -0.71
    arantine
    -0.70
    awei
    -0.70
    én
    -0.70
    mits
    -0.70
    POSITIVE LOGITS
     Ital
    0.80
    ————
    0.76
     Rouge
    0.74
     Royale
    0.71
    lette
    0.70
    eer
    0.69
    eers
    0.68
     Melody
    0.66
    ————————
    0.65
     ribbon
    0.65
    Activations Density 0.022%

    No Known Activations