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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 18793
    Prev
    Next
    INDEX
    Explanations

    words related to beads and jewelry

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bead" or related variations

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

    No Comments

    Negative Logits
     Grizzlies
    -0.79
    ©¶æ
    -0.70
    coni
    -0.64
     mosqu
    -0.64
     Libya
    -0.63
     Algeria
    -0.62
     Earthqu
    -0.62
     tomatoes
    -0.62
    OUP
    -0.60
     Mé
    -0.59
    POSITIVE LOGITS
    ead
    1.22
    amental
    0.90
    eson
    0.89
    nesses
    0.87
    umbnails
    0.83
    olor
    0.83
     beads
    0.82
    ress
    0.77
    ertodd
    0.77
    ed
    0.77
    Activations Density 0.013%

    No Known Activations