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. 4-RES-JB
    6. 5589
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Aquino."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Aqu" in various contexts, indicating a focus on topics related to "Aquaman" or similar associations

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

    No Comments

    Negative Logits
    Reloaded
    -0.77
    terday
    -0.73
    UGE
    -0.73
    FORMATION
    -0.71
    EngineDebug
    -0.69
    ãģį
    -0.67
     shroud
    -0.67
    PsyNetMessage
    -0.67
     fax
    -0.64
    âķIJâķIJ
    -0.64
    POSITIVE LOGITS
    arium
    1.14
    apon
    1.06
    alon
    1.04
    illus
    1.03
    acious
    1.02
    idon
    1.00
    arus
    0.97
    ilo
    0.96
    acity
    0.93
     Aqu
    0.93
    Activations Density 0.006%

    No Known Activations