© 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. 2-RES-JB
    11. 17659
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Chrom" with varying spellings and contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Chromium" software or related technologies

    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
    WARD
    -0.75
    riors
    -0.70
    OTAL
    -0.68
    ulton
    -0.68
     Lisbon
    -0.66
     PTS
    -0.65
    ggies
    -0.65
    PDATE
    -0.64
    VIS
    -0.63
     Presidents
    -0.62
    POSITIVE LOGITS
    ecast
    1.17
     chrom
    1.04
     Chrom
    1.01
    atin
    0.88
    chrom
    0.88
    atic
    0.86
    ancers
    0.85
    ograms
    0.84
    atography
    0.82
    ophon
    0.80
    Activations Density 0.007%

    No Known Activations