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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 12807
    Prev
    Next
    INDEX
    Explanations

    keywords related to living arrangements in a shared residence, specifically dormitories and roommates

    oai_token-act-pair · gpt-3.5-turbo

    references to dormitories and roommates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++++++++++++++++
    -0.73
    RAY
    -0.66
     visually
    -0.65
    ACA
    -0.64
     delegated
    -0.62
    SHIP
    -0.60
    */(
    -0.60
     Blessed
    -0.60
    OD
    -0.59
    Reviewed
    -0.59
    POSITIVE LOGITS
    itory
    1.43
    ancy
    1.01
     dorm
    0.99
    ysis
    0.99
    iott
    0.96
    uates
    0.95
    eret
    0.89
    iencies
    0.88
    iaries
    0.87
    ulty
    0.85
    Activations Density 0.007%

    No Known Activations