© 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. 12496
    Prev
    Next
    INDEX
    Explanations

    instances where a significant amount or level of something is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    the emphasis on the word "much" and its variations to convey degrees of intensity or quantity in various contexts

    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
    ipe
    -0.71
    umbn
    -0.67
    ubs
    -0.67
    thumbnails
    -0.66
    imens
    -0.65
    YN
    -0.64
    scripts
    -0.63
    wat
    -0.63
    izen
    -0.62
    roots
    -0.62
    POSITIVE LOGITS
    OTAL
    0.69
     anymore
    0.65
    bang
    0.64
     advertised
    0.59
     mattered
    0.58
     Guinness
    0.58
     Ballard
    0.58
     disson
    0.58
     regardless
    0.56
    ange
    0.55
    Activations Density 0.090%

    No Known Activations