© 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. 8650
    Prev
    Next
    INDEX
    Explanations

    sentences prompting the reader to click and read further

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the action of reading or accessing written content

    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
    endant
    -0.66
     Lans
    -0.64
    orph
    -0.63
    BuyableInstoreAndOnline
    -0.61
    Bridge
    -0.60
    opl
    -0.60
    pires
    -0.58
     imperson
    -0.58
    hod
    -0.58
    oses
    -0.58
    POSITIVE LOGITS
     HERE
    0.82
    SOURCE
    0.81
     firsthand
    0.77
     snipp
    0.73
     yours
    0.71
     yourself
    0.71
     plenty
    0.69
     COMPLE
    0.69
     here
    0.68
     fuller
    0.68
    Activations Density 0.083%

    No Known Activations