Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 415
    Prev
    Next
    INDEX
    Explanations

    the numerical values corresponding to different currencies

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts and currency values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Metatron
    -0.70
    idth
    -0.68
    ework
    -0.68
     timelines
    -0.66
    YN
    -0.65
     Investigations
    -0.64
     Moff
    -0.64
    umbn
    -0.63
     Enrique
    -0.63
    opic
    -0.63
    POSITIVE LOGITS
     apiece
    1.12
     ($
    1.09
     (£
    0.93
    -$
    0.90
     USD
    0.89
     per
    0.89
    worth
    0.88
    /$
    0.87
    âĤ¬
    0.84
    USD
    0.82
    Activations Density 0.074%

    No Known Activations