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. 9517
    Prev
    Next
    INDEX
    Explanations

    information related to financial transactions or deals.

    oai_token-act-pair · gpt-3.5-turbo

    financial transactions involving specific players in sports or media

    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
    ".
    -0.66
     elig
    -0.66
    ").
    -0.64
     inh
    -0.62
     appre
    -0.62
    !".
    -0.62
     indo
    -0.60
    .")
    -0.60
     AND
    -0.58
     ".
    -0.58
    POSITIVE LOGITS
     alike
    0.98
    axter
    0.78
    oliath
    0.77
     thereof
    0.64
    aughed
    0.61
    è£ħ
    0.60
     Others
    0.58
    ffe
    0.58
    ossal
    0.57
     colleagues
    0.57
    Activations Density 0.587%

    No Known Activations