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. 18094
    Prev
    Next
    INDEX
    Explanations

    references to concepts related to technology or computing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "og" which likely pertains to specific concepts or terminologies related to certain topics

    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
    terday
    -0.74
    ensional
    -0.70
    staking
    -0.64
     inadequ
    -0.64
     Leilan
    -0.62
     Hots
    -0.59
    IDENT
    -0.58
    wcs
    -0.57
    ples
    -0.57
    igned
    -0.55
    POSITIVE LOGITS
    roup
    1.24
    roups
    1.19
    allery
    1.12
    glers
    1.10
    gers
    1.08
    ues
    1.06
    gy
    1.02
    uchi
    1.02
    raphic
    0.98
    ogo
    0.93
    Activations Density 0.030%

    No Known Activations