© 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. 17249
    Prev
    Next
    INDEX
    Explanations

    keywords related to adventure and specific names such as "Wagner" and "Miyazaki"

    oai_token-act-pair · gpt-3.5-turbo

    references to adventure-themed content and notable figures associated with it

    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
     heav
    -0.75
    ĵĺ
    -0.72
     abdom
    -0.68
    heartedly
    -0.68
     hunger
    -0.64
    heed
    -0.64
     radiation
    -0.64
     toast
    -0.62
     photon
    -0.62
     grate
    -0.61
    POSITIVE LOGITS
    icist
    0.92
    ical
    0.91
    tions
    0.88
    encia
    0.87
    itech
    0.85
    swick
    0.85
    swer
    0.82
    stration
    0.81
    andise
    0.81
    ically
    0.81
    Activations Density 0.025%

    No Known Activations