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. 6-RES-JB
    6. 6512
    Prev
    Next
    INDEX
    Explanations

    entities related to "SU" or "SUSU" that may include organizations, events, or online communities

    oai_token-act-pair · gpt-3.5-turbo

    references to SUVs and related vehicle types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ferdinand
    -0.79
    rogens
    -0.67
    orius
    -0.67
    rics
    -0.66
     Turks
    -0.65
     Gutenberg
    -0.64
    working
    -0.64
    bug
    -0.61
    artisan
    -0.61
    work
    -0.60
    POSITIVE LOGITS
    arez
    1.15
    pper
    1.15
    zanne
    1.10
    pport
    1.02
    perm
    1.02
    icide
    1.01
    FFER
    0.98
    itable
    0.97
    pped
    0.96
    pping
    0.93
    Activations Density 0.020%

    No Known Activations