© 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. 21732
    Prev
    Next
    INDEX
    Explanations

    references to a specific city named "Makati"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Makati" and related entities

    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
     Quin
    -0.76
    iscal
    -0.71
    arton
    -0.69
    ellig
    -0.68
     Robertson
    -0.66
    idine
    -0.65
    oult
    -0.64
    forth
    -0.64
     recl
    -0.63
    çĭ
    -0.63
    POSITIVE LOGITS
     Miz
    1.58
     Mak
    1.57
    M
    1.47
     Mang
    1.44
     Mash
    1.44
     M
    1.44
     MH
    1.43
     MV
    1.43
     Mn
    1.38
     MTA
    1.38
    Activations Density 0.087%

    No Known Activations