© 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. 13568
    Prev
    Next
    INDEX
    Explanations

    numbers and values expressed in terms of percentage points

    oai_token-act-pair · gpt-3.5-turbo

    references to various percentage figures

    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
    enegger
    -0.62
    accompanied
    -0.62
    afort
    -0.62
    oust
    -0.62
     facult
    -0.62
     messenger
    -0.61
     lavish
    -0.60
    efer
    -0.60
     Poster
    -0.60
     Anon
    -0.59
    POSITIVE LOGITS
     points
    1.45
    points
    1.27
     point
    1.26
    point
    1.26
     Points
    1.05
     pts
    1.03
    Points
    1.03
    Point
    0.95
     pointers
    0.91
     Celsius
    0.90
    Activations Density 0.026%

    No Known Activations