© 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. 10157
    Prev
    Next
    INDEX
    Explanations

    descriptions of specific events or tasks

    oai_token-act-pair · gpt-3.5-turbo

    issues related to potential problems and challenges

    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
     whilst
    -0.62
    .","
    -0.58
     utilizing
    -0.58
    ÃĤ
    -0.57
    "},"
    -0.56
    ´
    -0.56
    aina
    -0.56
    ¨
    -0.55
    Ãĥ
    -0.55
    âĢİ
    -0.54
    POSITIVE LOGITS
     cops
    0.59
    istors
    0.59
     prosecutions
    0.58
     jurors
    0.58
     Clapper
    0.56
     testers
    0.55
    etheless
    0.54
    geries
    0.54
     contrace
    0.53
     anyway
    0.53
    Activations Density 2.367%

    No Known Activations