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. 5191
    Prev
    Next
    INDEX
    Explanations

    terms related to financial markets and economic activities

    oai_token-act-pair · gpt-3.5-turbo

    references to market conditions and trends

    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
     Lak
    -0.68
     Fas
    -0.67
     Drac
    -0.66
    bernatorial
    -0.65
     Protective
    -0.64
    tein
    -0.64
     Mountains
    -0.63
     Banner
    -0.63
    utan
    -0.62
    said
    -0.62
    POSITIVE LOGITS
    places
    1.63
    eers
    1.30
    hare
    1.22
    eer
    1.02
    place
    0.93
    eering
    0.88
    ability
    0.85
     Reloaded
    0.79
     stalls
    0.79
     downturn
    0.76
    Activations Density 0.059%

    No Known Activations