© 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. 22327
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential issues, challenges, threats, or risks

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presentation of challenges or risks

    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
    ithing
    -0.65
    animous
    -0.64
    lp
    -0.64
     Manufact
    -0.63
    rug
    -0.60
    achus
    -0.60
    yne
    -0.60
    follow
    -0.60
    base
    -0.60
    Base
    -0.60
    POSITIVE LOGITS
     difficulties
    1.29
     dangers
    1.26
     risks
    1.24
     challenges
    1.17
     problems
    1.17
     pitfalls
    1.17
     obstacles
    1.13
     opportunities
    1.09
     tremendous
    1.08
     hazards
    1.06
    Activations Density 0.198%

    No Known Activations