© 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. 9-RES-JB
    11. 15708
    Prev
    Next
    INDEX
    Explanations

    numeric values in the form of thousands

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Extras
    -0.69
    quickShipAvailable
    -0.67
     GEAR
    -0.59
    orously
    -0.58
    itionally
    -0.58
     Runes
    -0.58
    locks
    -0.56
     Lust
    -0.56
     Journals
    -0.56
     Parables
    -0.55
    POSITIVE LOGITS
     rating
    0.73
    ounce
    0.67
    hour
    0.65
    000
    0.64
    ottest
    0.63
    mile
    0.61
    issance
    0.59
    year
    0.59
    roller
    0.59
    797
    0.59
    Activations Density 0.099%

    No Known Activations