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. 11664
    Prev
    Next
    INDEX
    Explanations

    financial figures and amounts

    oai_token-act-pair · gpt-3.5-turbo

    numeric values related to financial figures

    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
    deen
    -0.70
     Fallen
    -0.67
     citiz
    -0.65
     Wid
    -0.65
    igrants
    -0.63
     Fist
    -0.61
    ittle
    -0.58
     hallway
    -0.58
    onga
    -0.57
     Sutherland
    -0.57
    POSITIVE LOGITS
    -$
    1.21
     billion
    1.09
     million
    1.01
    million
    0.99
     Billion
    0.99
    billion
    0.94
    bn
    0.92
    200
    0.90
     trillion
    0.88
     apiece
    0.85
    Activations Density 0.085%

    No Known Activations