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. 10612
    Prev
    Next
    INDEX
    Explanations

    phrases related to the flow of money or resources

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with financial transactions and resource management

    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
    tein
    -0.82
    ItemThumbnailImage
    -0.82
    taker
    -0.70
    ottesville
    -0.69
    CLASS
    -0.68
    FK
    -0.67
    feature
    -0.65
    artist
    -0.63
    \">
    -0.63
    è£
    -0.63
    POSITIVE LOGITS
    ients
    0.82
    phia
    0.82
     bloodstream
    0.80
    eros
    0.79
     fluids
    0.79
     toxins
    0.78
     gases
    0.76
    luent
    0.76
    ascus
    0.75
    urized
    0.75
    Activations Density 0.279%

    No Known Activations