© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18597
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs that suggest comparison or degree

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that imply uncertainty or potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vaugh
    -0.57
    farious
    -0.48
    chuk
    -0.47
     helicop
    -0.46
     Beir
    -0.45
     Moroc
    -0.44
    emale
    -0.44
     Rober
    -0.44
    ilaterally
    -0.44
    raltar
    -0.43
    POSITIVE LOGITS
     âĢº
    0.45
     depress
    0.42
    \":
    0.38
     nutshell
    0.38
    NESS
    0.38
     clutch
    0.38
     OFFIC
    0.37
     sw
    0.36
    âĦ¢:
    0.36
    nesses
    0.35
    Activations Density 1.656%

    No Known Activations