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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-RES-JB
    6. 16936
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Div" with varying numbers following it, possibly referring to different aspects within a certain context

    oai_token-act-pair · gpt-3.5-turbo

    references to divisions or categories, particularly within contexts like organizations or shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrase
    -0.71
     waivers
    -0.71
    eele
    -0.69
    DragonMagazine
    -0.69
     Helsinki
    -0.67
     TSA
    -0.67
     earnest
    -0.66
     BLM
    -0.66
    akeru
    -0.66
     account
    -0.64
    POSITIVE LOGITS
    orce
    1.23
    ISION
    1.05
    inational
    1.04
    isions
    1.02
    ination
    1.01
    isive
    0.99
    ertation
    0.88
    rael
    0.87
    ining
    0.87
    inators
    0.86
    Activations Density 0.005%

    No Known Activations