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. 11-RES-JB
    6. 4584
    Prev
    Next
    INDEX
    Explanations

    phrases related to different aspects of the market, such as market conditions, market trends, market strategies, and market movements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NEVER
    -0.75
     veto
    -0.65
     unpublished
    -0.64
     revoke
    -0.64
     genocide
    -0.63
     infall
    -0.62
     acknow
    -0.62
     miscar
    -0.62
     silence
    -0.62
     treason
    -0.61
    POSITIVE LOGITS
    hare
    1.06
     spurred
    0.91
     priced
    0.91
     attracting
    0.91
     amid
    0.90
     catering
    0.87
     vying
    0.86
     markets
    0.86
    places
    0.86
     thanks
    0.85
    Activations Density 0.339%

    No Known Activations