© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3631
    Prev
    Next
    INDEX
    Explanations

    references to fountains

    oai_token-act-pair · gpt-3.5-turbo

    references to fountains

    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
    eon
    -0.67
    edy
    -0.66
    VICE
    -0.65
    Alien
    -0.64
     Heller
    -0.63
    Ey
    -0.62
     WATCHED
    -0.62
     ACTIONS
    -0.62
    alien
    -0.61
     Consent
    -0.61
    POSITIVE LOGITS
     fountain
    1.36
     Fountain
    1.12
     pens
    0.92
    sonian
    0.84
    conservancy
    0.84
    issance
    0.81
     pen
    0.79
     empt
    0.78
    shire
    0.75
    tailed
    0.75
    Activations Density 0.006%

    No Known Activations