© 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. 12617
    Prev
    Next
    INDEX
    Explanations

    terms related to significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases pertaining to intentions, motivations, and prospects related to varying situations

    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
     hears
    -0.74
    votes
    -0.68
     installs
    -0.66
     conducts
    -0.65
     participates
    -0.64
     collects
    -0.64
    SHIP
    -0.63
    mits
    -0.61
    mails
    -0.61
     Uses
    -0.60
    POSITIVE LOGITS
     aren
    1.52
     are
    1.48
     weren
    1.42
     were
    1.29
     vary
    1.29
     differ
    1.26
     coincide
    1.17
     seem
    1.16
     ARE
    1.14
     remain
    1.12
    Activations Density 0.354%

    No Known Activations