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. 8-RES-JB
    6. 5506
    Prev
    Next
    INDEX
    Explanations

    words related to technology and networks, particularly those associated with encryption or online security

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "o" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REDACTED
    -0.76
     NCT
    -0.68
     Pax
    -0.64
     Rez
    -0.60
     Rampage
    -0.58
     occurrences
    -0.58
     Maid
    -0.57
     Alic
    -0.56
     Arist
    -0.56
     Newsp
    -0.56
    POSITIVE LOGITS
    gging
    1.36
    gged
    1.17
    ggle
    1.13
    pper
    1.12
    eping
    1.04
    pping
    1.01
    opy
    1.01
    opers
    1.00
    ppy
    1.00
    pped
    0.99
    Activations Density 0.113%

    No Known Activations