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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 21771
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to "Long Island"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 'Long' followed by various locations or terms associated with Long Island

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILA
    -0.74
    ħĭ
    -0.70
    ADRA
    -0.65
    natureconservancy
    -0.64
    IRO
    -0.61
    ICAN
    -0.61
    ILLE
    -0.61
     Flavoring
    -0.61
    ptive
    -0.59
    iances
    -0.59
    POSITIVE LOGITS
    itudinal
    1.36
    itud
    1.15
    itude
    1.02
    sword
    1.01
    shore
    0.97
    reads
    0.96
    enhagen
    0.94
    est
    0.93
    lasting
    0.92
    mire
    0.91
    Activations Density 0.031%

    No Known Activations