© 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. 3045
    Prev
    Next
    INDEX
    Explanations

    prefixes and suffixes enhancing the intensity or quality of a word

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant political or social dynamics

    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
     thanks
    -0.68
     guide
    -0.68
     microscope
    -0.68
     sergeant
    -0.67
     Ll
    -0.67
     dotted
    -0.66
     Heck
    -0.66
     slideshow
    -0.66
     nightmare
    -0.66
     dummy
    -0.66
    POSITIVE LOGITS
    arenthood
    1.28
    thood
    1.28
    iculture
    1.20
    Semitism
    1.13
    ankind
    1.09
    reating
    1.07
    ogenesis
    1.05
    iability
    1.03
    itism
    1.03
    ivism
    1.00
    Activations Density 0.401%

    No Known Activations