© 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. 10-RES-JB
    11. 3373
    Prev
    Next
    INDEX
    Explanations

    phrases representing different categories or options

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditional statements or options

    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
    Loading
    -0.71
    cv
    -0.57
    HCR
    -0.56
     ACT
    -0.55
    Sy
    -0.54
    Build
    -0.54
    RAW
    -0.53
    SA
    -0.53
    ibr
    -0.53
    expected
    -0.53
    POSITIVE LOGITS
     one
    1.69
    one
    1.56
     ONE
    1.35
     two
    1.32
    two
    1.32
     One
    1.27
     TWO
    1.25
    One
    1.14
     another
    1.14
     Two
    1.11
    Activations Density 0.168%

    No Known Activations