© 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. 21709
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to strong actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of existence or states

    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
    STEP
    -0.66
    æĸ¹
    -0.64
     Answers
    -0.63
     Dragonbound
    -0.63
    DragonMagazine
    -0.63
    èĢħ
    -0.63
     Borders
    -0.62
     Canary
    -0.62
     TAMADRA
    -0.62
     Whale
    -0.60
    POSITIVE LOGITS
    hing
    0.90
    cling
    0.88
    orical
    0.87
    ocol
    0.84
    abolic
    0.83
    gment
    0.82
    ¹
    0.82
    olith
    0.81
    umen
    0.80
    rency
    0.80
    Activations Density 0.170%

    No Known Activations