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. 19730
    Prev
    Next
    INDEX
    Explanations

    tech-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to business operations and structures

    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
     oneself
    -0.86
    uador
    -0.79
     herself
    -0.78
    cair
    -0.77
    tesy
    -0.76
    fax
    -0.73
    ording
    -0.73
    tale
    -0.73
    ocent
    -0.72
    istrate
    -0.71
    POSITIVE LOGITS
     portfolio
    1.20
     lineup
    1.07
     holdings
    1.07
     division
    1.07
     counterparts
    1.06
     counterpart
    1.04
     headquarters
    0.99
     arsenal
    0.99
     partners
    0.97
     strategy
    0.95
    Activations Density 0.539%

    No Known Activations