© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 15229
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    economic terms and discussions related to financial systems and their impacts

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

    No Comments

    Negative Logits
     pronouns
    -0.60
     masturbation
    -0.59
     tattoos
    -0.58
    Pict
    -0.56
    odiac
    -0.56
     epile
    -0.55
    Legend
    -0.55
     tattoo
    -0.55
     Guinness
    -0.54
     fame
    -0.54
    POSITIVE LOGITS
    economic
    0.88
     economically
    0.86
     unsustainable
    0.83
    Economic
    0.81
     trillions
    0.81
     economic
    0.81
     policymakers
    0.80
     economies
    0.79
     subsid
    0.77
     billions
    0.77
    Activations Density 3.512%

    No Known Activations