© 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. 11560
    Prev
    Next
    INDEX
    Explanations

    text related to computer programming or software development, specifically emphasizing actions involving code such as translation, copying source code, debugging, and beta testing

    oai_token-act-pair · gpt-3.5-turbo

    the word "for" in various contexts

    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
    IQ
    -0.79
    sonian
    -0.79
    edin
    -0.77
    soever
    -0.74
    hess
    -0.69
    ÃŃs
    -0.68
    Works
    -0.68
    hews
    -0.68
    omical
    -0.67
    displayText
    -0.67
    POSITIVE LOGITS
    geries
    1.21
    bidden
    1.12
    gery
    1.10
     sale
    0.96
     each
    0.92
     purposes
    0.92
     upcoming
    0.86
     inclusion
    0.82
     tonight
    0.80
     instance
    0.80
    Activations Density 0.208%

    No Known Activations