© 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. 0-RES-JB
    11. 15666
    Prev
    Next
    INDEX
    Explanations

    acronyms and codes related to news or information

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation "NA", which likely refers to a specific organization or context

    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
     gears
    -0.74
     Dirk
    -0.69
     stacks
    -0.68
     pens
    -0.63
     flats
    -0.62
     clutter
    -0.61
     Sto
    -0.61
     fortress
    -0.61
     harass
    -0.61
     Spurs
    -0.61
    POSITIVE LOGITS
    NA
    4.31
    NAS
    1.78
     NA
    1.64
    na
    1.58
    NE
    1.56
    NN
    1.51
    NC
    1.45
    NS
    1.42
    NES
    1.41
    SA
    1.34
    Activations Density 0.011%

    No Known Activations