© 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. 3-RES-JB
    11. 5813
    Prev
    Next
    INDEX
    Explanations

    references to the video game development company Obsidian Entertainment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Obs" 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
    WAYS
    -0.70
    WAY
    -0.68
    RANT
    -0.65
    lua
    -0.65
    ãĥĨãĤ£
    -0.65
    Fra
    -0.65
    ////////////////////////////////
    -0.64
    aneers
    -0.64
    boarding
    -0.64
    buster
    -0.64
    POSITIVE LOGITS
    erver
    1.29
    erving
    1.16
    olesc
    1.16
    ervation
    1.15
    olescent
    1.08
    erves
    1.07
    ensible
    1.04
    erv
    1.03
    icion
    1.02
    ound
    0.99
    Activations Density 0.009%

    No Known Activations