© 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. 8-RES-JB
    11. 4262
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "single player" and related phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "single-player" settings and housing terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Loren
    -0.71
    IVERS
    -0.68
     misinformation
    -0.67
    mos
    -0.64
    quickShipAvailable
    -0.64
     pains
    -0.62
     Danger
    -0.62
    ETA
    -0.61
    natureconservancy
    -0.61
    know
    -0.61
    POSITIVE LOGITS
    abyte
    0.79
    otide
    0.77
    handedly
    0.76
    arette
    0.72
    ottesville
    0.69
    anium
    0.68
    imester
    0.68
    undred
    0.68
     solitary
    0.68
    ucle
    0.66
    Activations Density 0.080%

    No Known Activations