© 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. 1526
    Prev
    Next
    INDEX
    Explanations

    phrases indicating events or actions

    oai_token-act-pair · gpt-3.5-turbo

    the use of the suffix "en."

    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
     CASE
    -0.61
     weekday
    -0.58
     quo
    -0.55
     EVER
    -0.54
     volts
    -0.54
    åĪ
    -0.53
     happening
    -0.52
     nationally
    -0.52
     ATL
    -0.52
     Triple
    -0.52
    POSITIVE LOGITS
    en
    4.03
    enic
    2.08
    eni
    2.07
    enf
    2.05
    ens
    2.01
    eny
    1.97
    EN
    1.91
    enes
    1.87
    eners
    1.78
    enh
    1.76
    Activations Density 0.032%

    No Known Activations