© 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. 9-RES-JB
    11. 13619
    Prev
    Next
    INDEX
    Explanations

    adjectives related to softness

    oai_token-act-pair · gpt-3.5-turbo

    instances of Pokémon-like descriptions, particularly those emphasizing physical attributes or types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reon
    -0.74
    uers
    -0.71
    naires
    -0.71
    OUGH
    -0.69
    agher
    -0.66
    DEV
    -0.64
     Ancients
    -0.63
     Pax
    -0.60
    ulhu
    -0.60
     âĸº
    -0.60
    POSITIVE LOGITS
    ening
    1.20
    ball
    1.17
    ener
    1.13
    hearted
    1.03
    cover
    1.00
     palate
    0.99
    eners
    0.96
    balls
    0.90
    core
    0.90
    ened
    0.89
    Activations Density 0.031%

    No Known Activations