© 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. 10263
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in 'tional' and 'autical'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to conditions, attributes, or characteristics, particularly in specialized contexts

    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
     Noir
    -0.71
    VK
    -0.66
    Frameworks
    -0.66
    hess
    -0.65
     Chimera
    -0.65
     Velvet
    -0.63
     Viz
    -0.63
    warts
    -0.63
     indisp
    -0.62
     massac
    -0.62
    POSITIVE LOGITS
    autical
    2.97
    itional
    2.34
     NASCAR
    1.41
     Rudd
    1.04
    orbit
    1.03
    omal
    1.01
    omical
    0.98
    orb
    0.93
    atl
    0.90
    itative
    0.84
    Activations Density 0.028%

    No Known Activations