© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 13311
    Prev
    Next
    INDEX
    Explanations

    words related to scripts or written instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "script" in various contexts

    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
     Geh
    -0.66
     Advocate
    -0.66
    favorite
    -0.65
     Bears
    -0.62
    CVE
    -0.61
     Nasa
    -0.61
     pend
    -0.59
     catast
    -0.59
     Lennon
    -0.59
     visitation
    -0.59
    POSITIVE LOGITS
    ions
    0.96
    ive
    0.92
    ript
    0.91
    л
    0.91
    onite
    0.90
    orsi
    0.90
    endium
    0.89
    orship
    0.87
    shaw
    0.87
    urally
    0.87
    Activations Density 0.014%

    No Known Activations