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. 9-RES-JB
    6. 19015
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of a "hub"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hub."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anguage
    -0.72
     graded
    -0.68
    terday
    -0.66
     extingu
    -0.64
     Grave
    -0.63
     Fang
    -0.63
     Antar
    -0.63
     choir
    -0.61
    uum
    -0.61
     menstrual
    -0.61
    POSITIVE LOGITS
    bub
    1.60
    bard
    1.32
    ris
    1.26
    lins
    1.16
    lot
    1.12
    bies
    1.05
    bing
    1.04
    bie
    1.04
    staff
    1.03
    hub
    0.97
    Activations Density 0.045%

    No Known Activations