© 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. 23854
    Prev
    Next
    INDEX
    Explanations

    action verbs (usually ending in -ing or -ed) related to specific events or situations

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate actions or concepts related to attendance, understanding, and engagement

    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
    ModLoader
    -0.67
     withd
    -0.65
     brow
    -0.65
     awa
    -0.65
    udeb
    -0.64
    catentry
    -0.63
    ueller
    -0.61
    knife
    -0.61
     stead
    -0.59
     enthusi
    -0.59
    POSITIVE LOGITS
    ments
    1.59
    ings
    1.53
    ment
    1.40
    ations
    1.37
    ATIONS
    1.31
    ances
    1.28
    INGS
    1.26
    ING
    1.21
    able
    1.20
    MENT
    1.20
    Activations Density 0.173%

    No Known Activations