© 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. 0-RES-JB
    11. 11366
    Prev
    Next
    INDEX
    Explanations

    mentions of someone being a guest

    oai_token-act-pair · gpt-3.5-turbo

    the word "guest" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matic
    -0.73
    byss
    -0.70
     Niet
    -0.68
     Indust
    -0.67
    û
    -0.64
    riers
    -0.64
    lust
    -0.63
    utics
    -0.63
    etsk
    -0.62
    Range
    -0.62
    POSITIVE LOGITS
     guest
    4.08
     Guest
    2.81
    Guest
    2.65
     guests
    2.59
     Guests
    2.03
     visitor
    1.53
     host
    1.40
     hosts
    1.33
     keynote
    1.24
     cameo
    1.14
    Activations Density 0.005%

    No Known Activations