Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7-RES-JB
    6. 6586
    Prev
    Next
    INDEX
    Explanations

    words related to powerful individuals in society or business

    oai_token-act-pair · gpt-3.5-turbo

    terms related to oligarchy and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grill
    -0.72
     Strong
    -0.68
     Remastered
    -0.66
     Hiroshima
    -0.66
     Denise
    -0.65
    leigh
    -0.65
     Worldwide
    -0.65
     Âł Âł Âł Âł
    -0.64
     Rank
    -0.64
    olver
    -0.64
    POSITIVE LOGITS
    archs
    1.27
    archy
    1.10
    ration
    1.07
    omen
    1.01
    eties
    0.98
    raph
    0.98
    elist
    0.97
    emate
    0.97
    opol
    0.97
    onial
    0.95
    Activations Density 0.052%

    No Known Activations