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. 3-RES-JB
    6. 19601
    Prev
    Next
    INDEX
    Explanations

    sequences describing digital timestamps in the format "00:HOURS:MINUTES"

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.74
    ascus
    -0.69
     sqor
    -0.68
    izont
    -0.67
    loo
    -0.64
    usterity
    -0.64
    ovan
    -0.64
    fired
    -0.64
    DragonMagazine
    -0.63
     offended
    -0.62
    POSITIVE LOGITS
     00
    1.18
    een
    0.93
     01
    0.89
    ees
    0.84
    ences
    0.83
    iry
    0.81
    encing
    0.80
    eenth
    0.80
    ington
    0.75
     000
    0.75
    Activations Density 0.014%

    No Known Activations