Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 8317
    Prev
    Next
    INDEX
    Explanations

    words related to beads or pearls

    oai_token-act-pair · gpt-3.5-turbo

    words related to beads and their quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grizzlies
    -0.68
     Oslo
    -0.65
     relativity
    -0.64
     911
    -0.61
     Yel
    -0.61
     citation
    -0.60
     Khe
    -0.60
     magnification
    -0.59
     Chrome
    -0.58
     NEC
    -0.57
    POSITIVE LOGITS
    ead
    1.55
    ertodd
    0.98
    eson
    0.94
    awan
    0.89
    eful
    0.87
    owship
    0.87
    cakes
    0.86
     beads
    0.86
    umbnails
    0.84
    abal
    0.84
    Activations Density 0.008%

    No Known Activations