© 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. 7753
    Prev
    Next
    INDEX
    Explanations

    text related to construction, design, and practical advice

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to practical advice and skill development

    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
     AND
    -0.58
    imester
    -0.54
    Scene
    -0.54
    ibrary
    -0.51
     HERE
    -0.49
     and
    -0.49
    yip
    -0.49
     et
    -0.49
    ©¶æ
    -0.48
    DragonMagazine
    -0.48
    POSITIVE LOGITS
     alike
    1.01
     accordingly
    0.89
     thereof
    0.88
     versa
    0.72
     thereto
    0.72
     thereafter
    0.71
     therein
    0.68
     afterward
    0.65
     respectively
    0.63
     consequently
    0.58
    Activations Density 2.224%

    No Known Activations