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. 5950
    Prev
    Next
    INDEX
    Explanations

    specific positions, titles, and roles of individuals within organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to official positions and entities in governance or law

    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
    ãĤ¢ãĥ«
    -0.54
    terday
    -0.52
    NetMessage
    -0.49
     behavi
    -0.49
    DragonMagazine
    -0.48
     Despair
    -0.48
    Ô
    -0.48
    hops
    -0.48
    thia
    -0.47
     Expand
    -0.47
    POSITIVE LOGITS
    osphere
    0.75
     equivalent
    0.61
    ultimate
    0.61
    icter
    0.59
    iest
    0.59
     department
    0.53
     abbre
    0.52
    liest
    0.51
    same
    0.51
     highest
    0.50
    Activations Density 0.974%

    No Known Activations