© 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. 2888
    Prev
    Next
    INDEX
    Explanations

    phrases related to division into categories or parts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating division or categorization

    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
    press
    -0.77
    iron
    -0.75
    aya
    -0.74
    dar
    -0.72
    eus
    -0.68
    gery
    -0.67
    nz
    -0.64
    inem
    -0.63
    WT
    -0.63
    efe
    -0.63
    POSITIVE LOGITS
     categories
    1.27
     manageable
    1.23
     subsections
    1.18
     separate
    1.17
     tiers
    1.16
     sections
    1.15
     phases
    1.15
     halves
    1.13
     thirds
    1.12
     smaller
    1.11
    Activations Density 0.096%

    No Known Activations