© 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. 7-RES-JB
    11. 21796
    Prev
    Next
    INDEX
    Explanations

    action verbs indicating physical movement or impact

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate actions or conditions impacting situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Extrem
    -0.60
     Leban
    -0.60
     Pengu
    -0.57
     inh
    -0.55
     UCHIJ
    -0.54
     inex
    -0.53
     Rue
    -0.52
     Vox
    -0.52
    REG
    -0.51
     shorth
    -0.50
    POSITIVE LOGITS
    able
    1.34
    ings
    1.17
    ables
    1.16
    ability
    1.14
    ingly
    1.06
    ably
    1.05
    ments
    1.04
    backs
    1.01
    holders
    0.99
    ibles
    0.92
    Activations Density 0.612%

    No Known Activations