© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 4052
    Prev
    Next
    INDEX
    Explanations

    terms related to role-playing games (RPGs), specifically in the context of a particular RPG system or content format

    oai_token-act-pair · gpt-3.5-turbo

    references to game elements or character attributes in role-playing games

    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
     Rey
    -0.84
    Syrian
    -0.82
    rams
    -0.74
    apolis
    -0.74
     Aleppo
    -0.73
    Tor
    -0.70
    ream
    -0.69
    anda
    -0.69
    rence
    -0.69
    amus
    -0.67
    POSITIVE LOGITS
    PF
    3.36
     PF
    3.11
    ogl
    1.45
     Gian
    1.22
     Stephenson
    1.10
     Fol
    1.04
     FG
    1.04
     Bagg
    1.03
     Treasurer
    1.01
    FG
    1.00
    Activations Density 0.057%

    No Known Activations