© 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. 3-RES-JB
    11. 180
    Prev
    Next
    INDEX
    Explanations

    references to the word "Plum" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to "plum" and "skim" along with other associated contexts

    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
    ettings
    -0.72
     opener
    -0.70
    ansas
    -0.65
     hug
    -0.64
    icate
    -0.61
     perjury
    -0.57
     latch
    -0.57
     prayer
    -0.57
     paddle
    -0.57
     conver
    -0.57
    POSITIVE LOGITS
    med
    0.93
     Plum
    0.86
    ontent
    0.86
    isode
    0.83
    estones
    0.81
    ONSORED
    0.81
    ————
    0.81
    ersed
    0.80
    ewater
    0.80
    etooth
    0.77
    Activations Density 0.024%

    No Known Activations