© 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. 8-RES-JB
    11. 2259
    Prev
    Next
    INDEX
    Explanations

    information related to informative sections and updates in a text

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements that counter common beliefs or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OnePlus
    -0.55
    ©¶æ
    -0.52
     Slate
    -0.51
    è¦ļéĨĴ
    -0.51
     Quan
    -0.50
     Cutter
    -0.50
     Duff
    -0.50
     Duchess
    -0.49
     Cerberus
    -0.47
    iceps
    -0.47
    POSITIVE LOGITS
     respectively
    0.83
    ertain
    0.62
    .","
    0.59
     versa
    0.58
    they
    0.57
     themselves
    0.56
    soType
    0.55
    .</
    0.55
    lems
    0.54
    .).
    0.53
    Activations Density 1.721%

    No Known Activations