© 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. 8-RES-JB
    11. 2522
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a person or entity taking a specific action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "has" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eem
    -0.74
    Newsletter
    -0.70
    raw
    -0.66
     behold
    -0.65
    seless
    -0.62
    etting
    -0.61
    ItemThumbnailImage
    -0.61
    ecd
    -0.61
    catentry
    -0.61
    jam
    -0.60
    POSITIVE LOGITS
     been
    1.37
    been
    1.16
     undergone
    1.14
     become
    1.11
     apologised
    1.08
     begun
    1.06
     emerged
    1.06
     teamed
    0.96
     gotten
    0.95
     reportedly
    0.94
    Activations Density 0.235%

    No Known Activations