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. 8-RES-JB
    6. 14637
    Prev
    Next
    INDEX
    Explanations

    words related to financial reserves

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "reserve" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acles
    -0.81
    Īè
    -0.74
    fixes
    -0.74
    ī
    -0.66
    OTO
    -0.65
    redd
    -0.65
    src
    -0.63
    tons
    -0.63
    RESULTS
    -0.63
    romeda
    -0.63
    POSITIVE LOGITS
     reserve
    0.85
     reserves
    0.75
    oir
    0.74
    folios
    0.72
     Reserve
    0.72
     reservation
    0.70
     reserv
    0.69
    inent
    0.69
    erness
    0.67
    Bank
    0.67
    Activations Density 0.050%

    No Known Activations