© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20636
    Prev
    Next
    INDEX
    Explanations

    long verbs related to evaluating, analyzing, or causing risks or potential harm

    oai_token-act-pair · gpt-3.5-turbo

    words related to risk, scrutiny, and political concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REE
    -0.65
    auri
    -0.61
    erity
    -0.59
    ree
    -0.59
     Wad
    -0.57
     Anger
    -0.56
    Notable
    -0.55
    tags
    -0.55
    ritz
    -0.55
    elf
    -0.55
    POSITIVE LOGITS
    izing
    2.82
    ized
    2.82
    ization
    2.65
    izes
    2.61
    ize
    2.61
    ised
    2.56
    ising
    2.45
    izers
    2.44
    izations
    2.40
    isation
    2.35
    Activations Density 0.198%

    No Known Activations