© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 9856
    Prev
    Next
    INDEX
    Explanations

    mentions of different groups of people in various contexts, such as researchers, voters, consumers, individuals, players, Jews, and liberals

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people or individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stars
    -0.64
    ces
    -0.61
     Shore
    -0.61
    ILE
    -0.61
    aughs
    -0.60
    Aw
    -0.60
    UV
    -0.59
    DOWN
    -0.58
    sie
    -0.58
    shows
    -0.58
    POSITIVE LOGITS
     are
    1.10
     aren
    1.03
     perceive
    0.98
     prefer
    0.97
     have
    0.97
     were
    0.95
     everywhere
    0.94
     crave
    0.93
     realize
    0.91
     weren
    0.91
    Activations Density 0.294%

    No Known Activations