© 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. 9-RES-JB
    11. 5362
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential problems or crises

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating severe consequences of climate change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obbies
    -0.74
    reetings
    -0.70
     nods
    -0.66
    estones
    -0.66
    stad
    -0.65
     homage
    -0.65
     pronouns
    -0.65
     Creed
    -0.64
    noon
    -0.64
     admire
    -0.64
    POSITIVE LOGITS
     irreversible
    1.30
     havoc
    1.27
     destabil
    1.26
     catastrophic
    1.12
     exacerb
    1.11
     Worse
    1.07
     damaging
    1.07
     worsening
    1.07
     exacerbate
    1.06
     instability
    1.05
    Activations Density 0.720%

    No Known Activations