© 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. 7-RES-JB
    11. 23811
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with "Prim" in a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    the term "Prim" and its variations, indicating a focus on the concept of 'prim' or 'primitive'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IGH
    -0.82
    lihood
    -0.80
    UGH
    -0.74
     Graveyard
    -0.73
    UGE
    -0.66
    IELD
    -0.66
    hiro
    -0.64
     Bard
    -0.63
     Cheong
    -0.62
     Hanson
    -0.61
    POSITIVE LOGITS
    itives
    1.65
    ordial
    1.45
    itive
    1.33
    acy
    1.12
    itiveness
    1.10
    rose
    1.07
    arily
    1.05
    eness
    1.02
    etime
    1.01
    archs
    0.95
    Activations Density 0.027%

    No Known Activations