Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21876
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific printer model, "HP Multi Jet Fusion" - possibly indicating a technical interest in the printer and its associated software

    oai_token-act-pair · gpt-3.5-turbo

    references to specific jet systems and technologies associated with aircraft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DPR
    -0.91
     Yanukovych
    -0.84
     Yanuk
    -0.81
     poss
    -0.80
    umbledore
    -0.78
     GOODMAN
    -0.76
    sov
    -0.73
     territ
    -0.72
    annis
    -0.71
     Assange
    -0.70
    POSITIVE LOGITS
     Jet
    3.63
    Jet
    3.32
    jet
    1.61
     Laser
    1.28
     Jets
    1.25
     Southwest
    1.20
     Turbo
    1.18
     Astro
    1.15
     Gale
    1.10
     Chili
    1.06
    Activations Density 0.033%

    No Known Activations