© 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. 3228
    Prev
    Next
    INDEX
    Explanations

    phrases with emphasis on the quantity or exclusivity of certain objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate possession or existence

    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
    TG
    -0.74
    ensing
    -0.72
    SHIP
    -0.68
     territ
    -0.66
    Interested
    -0.63
    Tweet
    -0.62
    PHOTOS
    -0.61
    bart
    -0.59
    eem
    -0.58
    responsible
    -0.58
    POSITIVE LOGITS
     been
    1.35
     undergone
    1.19
    been
    1.17
     Been
    1.07
    kell
    1.02
     existed
    0.98
     similarities
    0.98
     become
    0.96
     implications
    0.95
     arisen
    0.95
    Activations Density 0.303%

    No Known Activations