© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16125
    Prev
    Next
    INDEX
    Explanations

    names, abbreviations, and terms related to organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    specific acronyms, names, and complex identifiers related to organizations or individuals

    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
    taboola
    -1.22
    ioxide
    -0.67
    BILITIES
    -0.65
    degree
    -0.64
    ciating
    -0.62
    iture
    -0.60
    lishing
    -0.60
     guiActiveUnfocused
    -0.60
    webkit
    -0.60
     pse
    -0.58
    POSITIVE LOGITS
    inki
    1.13
    igans
    0.81
    puff
    0.74
     sap
    0.73
    idan
    0.73
     Abedin
    0.71
    quarters
    0.71
    ournals
    0.71
    ĸļ
    0.70
    nian
    0.70
    Activations Density 0.365%

    No Known Activations