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. 9-RES-JB
    6. 11044
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic indicators, specifically focusing on pricing and costs

    oai_token-act-pair · gpt-3.5-turbo

    references to housing and oil prices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lich
    -0.72
    hood
    -0.69
    issance
    -0.68
    BUG
    -0.67
    less
    -0.66
    iverse
    -0.64
     Squadron
    -0.64
    shield
    -0.64
     Identity
    -0.63
    JECT
    -0.63
    POSITIVE LOGITS
    cape
    1.29
    paces
    1.29
    poons
    1.24
    pring
    1.23
    pace
    1.12
    cale
    1.09
    hare
    1.07
    heet
    1.07
    hips
    1.04
    chool
    0.99
    Activations Density 0.148%

    No Known Activations