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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 17394
    Prev
    Next
    INDEX
    Explanations

    references to money or financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "money" and its variations

    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
    ICLE
    -0.91
    dq
    -0.78
    Temperature
    -0.67
    Earth
    -0.66
    IELD
    -0.65
    \/\/
    -0.64
     Halls
    -0.64
    spect
    -0.63
     Sed
    -0.63
    DAQ
    -0.61
    POSITIVE LOGITS
     laundering
    1.30
    bags
    1.00
    dollar
    0.84
     invested
    0.84
     appropriated
    0.80
    aundering
    0.79
    frame
    0.78
     owed
    0.78
    bag
    0.77
     money
    0.77
    Activations Density 0.046%

    No Known Activations