© 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. 0-RES-JB
    11. 16578
    Prev
    Next
    INDEX
    Explanations

    phrases related to reservations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reservation."

    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
     reservations
    -0.88
    gur
    -0.82
     revisions
    -0.74
    codes
    -0.68
    Thumbnail
    -0.67
    Bul
    -0.67
    irin
    -0.65
    aganda
    -0.64
    sv
    -0.63
    pir
    -0.62
    POSITIVE LOGITS
     reservation
    1.20
    anqu
    0.75
    iance
    0.69
     Kendrick
    0.64
    iste
    0.63
     locality
    0.62
     Moment
    0.62
    Jew
    0.60
     causation
    0.60
     yourselves
    0.60
    Activations Density 0.000%

    No Known Activations