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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 18736
    Prev
    Next
    INDEX
    Explanations

    important and relevant information or content in news articles

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing significant or impactful issues and stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abase
    -0.70
    gom
    -0.58
    vae
    -0.57
    anz
    -0.55
    nar
    -0.54
    kered
    -0.54
    ruary
    -0.53
     plur
    -0.53
    TY
    -0.52
    lite
    -0.52
    POSITIVE LOGITS
    Untitled
    0.58
    EngineDebug
    0.57
    icter
    0.57
    ecast
    0.57
    ãĤ´ãĥ³
    0.56
    edIn
    0.55
    ô
    0.55
     Codec
    0.54
     Unc
    0.53
    ĪĴ
    0.52
    Activations Density 0.024%

    No Known Activations