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. 9774
    Prev
    Next
    INDEX
    Explanations

    monetary values

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts represented with dollar signs

    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
     Tall
    -0.77
     isolation
    -0.73
     interf
    -0.73
     Tid
    -0.70
     exerc
    -0.68
     compe
    -0.66
     Vid
    -0.66
     assum
    -0.66
     commun
    -0.66
     Sed
    -0.65
    POSITIVE LOGITS
    $$
    1.43
    $$$$
    1.38
    250
    1.20
     Donation
    1.19
    100
    1.18
    500
    1.14
    1000
    1.13
    350
    1.13
    150
    1.12
    5000
    1.12
    Activations Density 0.068%

    No Known Activations