© 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. 10-RES-JB
    11. 11264
    Prev
    Next
    INDEX
    Explanations

    phrases expressing thoughts, opinions, beliefs, or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal beliefs and thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntil
    -0.61
    orio
    -0.59
    Merit
    -0.57
    endment
    -0.56
    imen
    -0.55
    Poké
    -0.54
     meanwhile
    -0.53
    eeper
    -0.53
    0000000
    -0.53
    uty
    -0.52
    POSITIVE LOGITS
     belongs
    1.26
     constitutes
    1.22
     deserves
    1.21
     could
    1.18
     exists
    1.16
     ought
    1.15
     will
    1.14
     represents
    1.13
     qualifies
    1.10
     would
    1.10
    Activations Density 0.112%

    No Known Activations