© 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. 9-RES-JB
    6. 7271
    Prev
    Next
    INDEX
    Explanations

    mentions of the abbreviation "NY."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation or reference to "New York."

    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
    ayne
    -0.75
    ainer
    -0.71
    rador
    -0.71
    heimer
    -0.69
    iance
    -0.68
    ENTION
    -0.66
    endish
    -0.65
    iffin
    -0.64
    /+
    -0.64
    INGTON
    -0.63
    POSITIVE LOGITS
    mph
    1.08
    heter
    1.01
     Mellon
    0.92
    eah
    0.91
    acht
    0.90
    eon
    0.81
    tics
    0.79
    times
    0.76
    ti
    0.75
    mbol
    0.75
    Activations Density 0.069%

    No Known Activations