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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 472
    Prev
    Next
    INDEX
    Explanations

    words that start with 'dwarf' or related forms like 'dwarfs' and 'dwarfed'

    oai_token-act-pair · gpt-4-turbo

    words related to dwarves

    oai_token-act-pair · gpt-3.5-turbo

    references to "dwarf" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orie
    -0.88
    inventoryQuantity
    -0.75
    ifice
    -0.74
    choes
    -0.73
    uberty
    -0.71
    apego
    -0.70
    mble
    -0.68
     philos
    -0.68
    EV
    -0.67
    iren
    -0.66
    POSITIVE LOGITS
     dwarf
    1.01
     Dwarf
    0.93
     Dwar
    0.90
     dwarves
    0.88
     tuberculosis
    0.76
    sson
    0.70
    ishly
    0.69
     dwar
    0.69
     elves
    0.68
    alf
    0.68
    Activations Density 0.011%

    No Known Activations