© 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. 11626
    Prev
    Next
    INDEX
    Explanations

    phrases related to obstacles or hindrances

    oai_token-act-pair · gpt-3.5-turbo

    elements related to obstacles and interference in physical or metaphorical journeys

    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
     Remastered
    -0.76
     recipes
    -0.73
     Recipes
    -0.73
     Savings
    -0.70
     regrets
    -0.69
     confession
    -0.68
     gratitude
    -0.67
    İĭ
    -0.65
    ulz
    -0.64
    prom
    -0.62
    POSITIVE LOGITS
     penetrate
    1.24
     traverse
    1.24
     travers
    1.22
     collide
    1.17
     obstruct
    1.17
     penet
    1.07
     impede
    1.07
     crossing
    1.06
     intersect
    1.06
     maneuver
    1.04
    Activations Density 0.628%

    No Known Activations