© 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. 16405
    Prev
    Next
    INDEX
    Explanations

    words related to the Vietnamese city of Hanoi

    oai_token-act-pair · gpt-3.5-turbo
    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
     ISI
    -0.67
     «
    -0.64
     NXT
    -0.62
     visionary
    -0.61
     ref
    -0.61
     sterile
    -0.61
     insol
    -0.60
     dispensaries
    -0.60
     ushered
    -0.60
     instructions
    -0.57
    POSITIVE LOGITS
    bon
    4.72
    bons
    2.00
    Bon
    1.77
     bon
    1.53
    bone
    1.37
    bones
    1.27
     Bon
    1.26
    ban
    1.10
    bo
    1.10
    boa
    1.09
    Activations Density 0.006%

    No Known Activations