© 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. 16128
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "contain" or similar forms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contamination or related environmental issues

    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
    ãĤ¬
    -0.74
    manship
    -0.71
    EStream
    -0.70
    STER
    -0.68
    lihood
    -0.67
    STD
    -0.67
     scratch
    -0.66
    ħĭ
    -0.64
    OPLE
    -0.63
    ï¸
    -0.62
    POSITIVE LOGITS
    ributed
    1.45
    roversial
    1.36
    ribution
    1.35
    rovers
    1.35
    ribute
    1.27
    emporary
    1.27
    ribut
    1.26
    rollers
    1.26
    inent
    1.25
    ainers
    1.23
    Activations Density 0.036%

    No Known Activations