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. 2942
    Prev
    Next
    INDEX
    Explanations

    mentions of financial activities and investments

    oai_token-act-pair · gpt-3.5-turbo

    financial investment activities and projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     incorrect
    -0.83
     sins
    -0.83
     dishon
    -0.79
     unfor
    -0.77
     torment
    -0.76
    emort
    -0.76
     abuser
    -0.76
     unbearable
    -0.75
     insults
    -0.75
    deen
    -0.75
    POSITIVE LOGITS
     pioneered
    0.98
     startups
    0.96
     Panasonic
    0.89
     partnerships
    0.84
     Startup
    0.82
     accelerator
    0.82
     consortium
    0.82
     pioneering
    0.80
     partnering
    0.80
     startup
    0.80
    Activations Density 0.811%

    No Known Activations