© 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
    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. 3702
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, especially "Shay" and "Airbnb"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and companies, particularly those associated with the name "Shay" and the brand "Airbnb"

    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
    rh
    -0.86
    inker
    -0.83
    addle
    -0.82
    swick
    -0.80
    gars
    -0.79
    cock
    -0.79
    phthal
    -0.76
    asses
    -0.75
    ptroller
    -0.75
    pse
    -0.75
    POSITIVE LOGITS
    20439
    0.83
    âĺħâĺħ
    0.77
    ãĥ£
    0.76
    BOOK
    0.70
    è¦ļéĨĴ
    0.70
    ãģ¦
    0.63
    DERR
    0.62
    RAFT
    0.61
     Feldman
    0.61
     Awakens
    0.61
    Activations Density 0.112%

    No Known Activations