Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20104
    Prev
    Next
    INDEX
    Explanations

    phrases related to the place name "Flushing."

    oai_token-act-pair · gpt-3.5-turbo

    instances of various forms of the word "push" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.70
    edom
    -0.68
    oreal
    -0.68
     Survive
    -0.63
     surv
    -0.63
    Mach
    -0.63
     redes
    -0.62
    heid
    -0.61
     rele
    -0.61
     Ribbon
    -0.59
    POSITIVE LOGITS
     Meadows
    1.07
    ushing
    0.91
    ushes
    0.83
    aukee
    0.81
    ush
    0.78
    inx
    0.77
     Crusade
    0.74
    vier
    0.71
    ushed
    0.71
    itably
    0.67
    Activations Density 0.010%

    No Known Activations