© 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. 409
    Prev
    Next
    INDEX
    Explanations

    words related to tools or objects associated with tabletop activities or games

    oai_token-act-pair · gpt-3.5-turbo

    references to tabletop gaming and miniature figures

    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
    ree
    -0.71
     Cit
    -0.71
    Que
    -0.70
     transitional
    -0.69
    lean
    -0.68
    oj
    -0.68
     navig
    -0.67
     Sioux
    -0.67
     interpol
    -0.67
    Bank
    -0.67
    POSITIVE LOGITS
     Warhammer
    2.95
     tabletop
    2.07
    hammer
    1.86
     miniature
    1.84
    iatures
    1.79
     Imperium
    1.67
     Drac
    1.28
     Cth
    1.27
     Dresden
    1.22
     Mech
    1.19
    Activations Density 0.062%

    No Known Activations