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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21924
    Prev
    Next
    INDEX
    Explanations

    references to a specific company or platform called "Hub"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Hub" and its variations, indicating a focus on a central organization or platform

    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
    Downloadha
    -0.94
    anguage
    -0.83
    vironment
    -0.75
    terday
    -0.72
     Gael
    -0.69
    esthetic
    -0.68
     kindred
    -0.67
    uary
    -0.67
    sembly
    -0.67
    DonaldTrump
    -0.67
    POSITIVE LOGITS
    hub
    1.23
    Hub
    1.11
    lot
    1.10
    bub
    1.09
    bard
    1.06
     Hub
    1.04
    staff
    0.97
    rod
    0.94
    bles
    0.94
    bell
    0.93
    Activations Density 0.011%

    No Known Activations