© 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. 0-RES-JB
    11. 2070
    Prev
    Next
    INDEX
    Explanations

    words containing the subsequence "rom" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "rom" in various contexts

    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
     fields
    -0.72
     overtime
    -0.67
     folds
    -0.66
     field
    -0.65
     Fields
    -0.64
     Dakota
    -0.63
     Fei
    -0.63
     abl
    -0.63
     Keen
    -0.62
     attributes
    -0.62
    POSITIVE LOGITS
    rom
    4.49
    rome
    2.50
    roma
    2.36
    ROM
    1.85
    romancer
    1.72
    rog
    1.53
    roman
    1.51
    roph
    1.50
    Rom
    1.50
    ros
    1.44
    Activations Density 0.018%

    No Known Activations