© 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. 3497
    Prev
    Next
    INDEX
    Explanations

    references to built-in features or components within various products or technologies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to construction or assembly

    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
    ilts
    -0.64
    illi
    -0.58
    ricular
    -0.56
    adia
    -0.54
    ities
    -0.51
    ITIES
    -0.51
    é¾įå
    -0.49
    illary
    -0.48
    olic
    -0.48
    ility
    -0.48
    POSITIVE LOGITS
    -
    1.52
    âĢij
    1.34
    âĢIJ
    1.25
    -[
    1.15
    -'
    1.11
     versa
    1.00
    -(
    0.99
    -$
    0.98
    -.
    0.98
    -)
    0.93
    Activations Density 0.484%

    No Known Activations