© 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. 6271
    Prev
    Next
    INDEX
    Explanations

    phrases related to asking questions or seeking information

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "what" 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
    enburg
    -0.84
    robe
    -0.73
    gur
    -0.73
    gi
    -0.68
    xon
    -0.67
    kj
    -0.66
    odge
    -0.60
    uge
    -0.60
    arella
    -0.60
     favor
    -0.58
    POSITIVE LOGITS
     transpired
    1.39
     happens
    1.34
     happened
    1.30
     constitutes
    1.21
    soever
    1.09
     awaits
    0.99
     separates
    0.97
     happ
    0.97
     exactly
    0.96
     constituted
    0.94
    Activations Density 0.107%

    No Known Activations