© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5519
    Prev
    Next
    INDEX
    Explanations

    expressions related to praise or criticism, especially in the form of feedback or judgment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pat" in various contexts

    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
     Emin
    -0.68
     Matter
    -0.66
    omething
    -0.65
    CV
    -0.64
     Galile
    -0.63
     Sins
    -0.63
     Archangel
    -0.62
    ource
    -0.61
    theless
    -0.61
     Controlled
    -0.60
    POSITIVE LOGITS
    rolled
    1.22
    reon
    1.22
    hetically
    1.21
    tered
    1.19
    terson
    1.19
    ters
    1.18
    ting
    1.17
    ty
    1.11
    ricia
    1.08
    riots
    1.07
    Activations Density 0.041%

    No Known Activations