© 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. 6-RES-JB
    11. 2673
    Prev
    Next
    INDEX
    Explanations

    references to dwarf-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of dwarfs and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orie
    -0.85
    inventoryQuantity
    -0.81
    alez
    -0.75
    mble
    -0.73
    uberty
    -0.71
    ored
    -0.71
    ettings
    -0.70
     antioxid
    -0.67
     Clip
    -0.67
    creen
    -0.66
    POSITIVE LOGITS
     Dwarf
    0.87
     Fortress
    0.77
    ishly
    0.76
     elves
    0.75
    esses
    0.74
     Dwar
    0.74
     dwarves
    0.73
     dwarf
    0.73
    fs
    0.72
    founded
    0.69
    Activations Density 0.024%

    No Known Activations