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. 57
    Prev
    Next
    INDEX
    Explanations

    terms related to salaries or payment

    oai_token-act-pair · gpt-3.5-turbo

    references to payment-related concepts

    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
    GGGGGGGG
    -0.71
     Uriel
    -0.70
     Nare
    -0.69
     Veg
    -0.68
     Scotia
    -0.66
     Dresden
    -0.63
     constitu
    -0.61
     Giov
    -0.61
    FTWARE
    -0.61
     Frankfurt
    -0.61
    POSITIVE LOGITS
    outs
    1.38
    checks
    1.36
    roll
    1.15
    back
    1.14
    offs
    1.09
    backs
    1.03
    wall
    0.99
    ments
    0.95
    days
    0.94
    tm
    0.92
    Activations Density 0.037%

    No Known Activations