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. 6-RES-JB
    6. 22777
    Prev
    Next
    INDEX
    Explanations

    references to various volcanic eruptions, lava flows, and geological formations

    oai_token-act-pair · gpt-3.5-turbo

    references to volcanic mountains and their eruptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bye
    -0.64
    staking
    -0.61
     ADS
    -0.61
     Hyundai
    -0.58
    BACK
    -0.58
    ulative
    -0.58
     Jinn
    -0.56
    ÑĮ
    -0.56
     bottled
    -0.56
     actionGroup
    -0.55
    POSITIVE LOGITS
    burgh
    0.75
    eneg
    0.74
    pload
    0.68
     Reserv
    0.67
    api
    0.63
    heny
    0.62
     reservoirs
    0.61
     unpop
    0.61
    pees
    0.60
    obl
    0.60
    Activations Density 0.089%

    No Known Activations