© 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. 3081
    Prev
    Next
    INDEX
    Explanations

    acronyms related to organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to organizational acronyms or abbreviations

    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
    gets
    -0.75
    things
    -0.72
     Mayweather
    -0.72
     Merkel
    -0.70
     Witt
    -0.69
     Michaels
    -0.68
     Gork
    -0.68
     Gingrich
    -0.68
     Kut
    -0.66
    birth
    -0.65
    POSITIVE LOGITS
    ombat
    1.13
    OC
    1.11
    aml
    1.03
    ontent
    0.99
    onut
    0.99
    culus
    0.98
    entric
    0.98
    urrencies
    0.97
    abulary
    0.97
    omb
    0.97
    Activations Density 0.007%

    No Known Activations