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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 14685
    Prev
    Next
    INDEX
    Explanations

    currency terms, financial market references, and economic indicators

    oai_token-act-pair · gpt-3.5-turbo

    key economic and political terms related to the Australian dollar and the Democratic Party

    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
    Sov
    -0.79
     confir
    -0.73
    ivas
    -0.69
    ĨĴ
    -0.69
    å¦
    -0.67
    DEP
    -0.66
    vari
    -0.66
    Īè
    -0.65
    GMT
    -0.65
     pestic
    -0.65
    POSITIVE LOGITS
    eers
    0.82
     itself
    0.81
    Thumbnail
    0.72
    ousel
    0.71
    allery
    0.67
    mma
    0.66
     debacle
    0.66
     fiasco
    0.66
    enium
    0.65
    liner
    0.65
    Activations Density 0.287%

    No Known Activations