© 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. 4-RES-JB
    11. 698
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical procedures or health conditions

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" and its variations in different contexts

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

    No Comments

    Negative Logits
     Vaugh
    -0.73
     Afgh
    -0.63
     Jagu
    -0.62
    dn
    -0.62
    edIn
    -0.62
    Eth
    -0.60
    chuk
    -0.60
     eg
    -0.59
     [*
    -0.58
    Attach
    -0.57
    POSITIVE LOGITS
     nutshell
    0.75
     steady
    0.75
    cess
    0.72
     generous
    0.70
    cknowled
    0.69
     glimpse
    0.69
     lot
    0.68
     bunch
    0.67
    ird
    0.67
     reliable
    0.64
    Activations Density 0.108%

    No Known Activations