© 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. 23548
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms related to various technical terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to medical and technical terms

    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
    ãĥ³ãĤ¸
    -0.78
     Volks
    -0.76
    taboola
    -0.74
     UNIVERS
    -0.73
    bern
    -0.73
     WATCHED
    -0.71
    wcsstore
    -0.71
     unfocusedRange
    -0.70
    é¾įåĸļ士
    -0.70
    ãĤ¶
    -0.69
    POSITIVE LOGITS
    Gs
    1.02
    Fs
    0.90
    Ms
    0.86
    Ds
    0.85
    Ns
    0.83
    Vs
    0.80
     prevention
    0.79
     certification
    0.77
    Cs
    0.74
     compliant
    0.74
    Activations Density 0.180%

    No Known Activations