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. 10-RES-JB
    6. 10813
    Prev
    Next
    INDEX
    Explanations

    terms related to financial debts or unpaid amounts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "re"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rabb
    -0.69
     Chinatown
    -0.65
     Phar
    -0.64
     EntityItem
    -0.64
     sourcing
    -0.62
     Garfield
    -0.59
     gag
    -0.57
    circ
    -0.57
     Taxi
    -0.57
     faint
    -0.56
    POSITIVE LOGITS
    cht
    1.27
    bral
    1.21
    cks
    1.16
    xit
    1.14
    ngth
    1.10
    versible
    1.05
    zza
    1.04
    asury
    1.03
    kson
    1.03
    porter
    1.02
    Activations Density 0.036%

    No Known Activations