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. 927
    Prev
    Next
    INDEX
    Explanations

    words related to disputing, objecting, or suppressing something

    oai_token-act-pair · gpt-3.5-turbo

    words associated with the concept of "quelling" or suppressing something

    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
    HAEL
    -0.73
    croft
    -0.71
    strap
    -0.66
    baugh
    -0.65
     à¨
    -0.64
     mock
    -0.63
     Province
    -0.63
     permitting
    -0.62
     warranties
    -0.61
    AGES
    -0.60
    POSITIVE LOGITS
    arre
    1.20
    idd
    1.17
    iets
    1.05
    arant
    1.01
    ivering
    1.01
    ibble
    0.99
    atro
    0.98
    icks
    0.98
    arantine
    0.97
    itter
    0.96
    Activations Density 0.023%

    No Known Activations