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. 3-RES-JB
    6. 21978
    Prev
    Next
    INDEX
    Explanations

    references to a specific platform or brand referred to as "Hub"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Hub" or related branding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.91
    anguage
    -0.77
    DonaldTrump
    -0.77
    terday
    -0.75
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.73
    esthetic
    -0.71
    izers
    -0.68
    uary
    -0.67
     Samoa
    -0.67
    chnology
    -0.67
    POSITIVE LOGITS
    bub
    1.31
    hub
    1.30
    bard
    1.23
    Hub
    1.22
    bies
    1.08
     Hub
    1.07
    lot
    1.05
    rod
    1.05
    staff
    1.04
    bles
    1.02
    Activations Density 0.007%

    No Known Activations