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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20914
    Prev
    Next
    INDEX
    Explanations

    words related to superlatives or extremes

    oai_token-act-pair · gpt-3.5-turbo

    key terms associated with high-impact concepts or extreme conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Decoder
    -0.75
     Jackets
    -0.66
     Dragons
    -0.65
     Waves
    -0.65
     flats
    -0.62
     Writers
    -0.62
     Pax
    -0.60
     Generator
    -0.60
     Growth
    -0.60
     waivers
    -0.59
    POSITIVE LOGITS
    fficient
    1.06
    erous
    1.05
    icable
    1.05
    accessible
    1.04
    isable
    1.04
    icent
    1.03
    istic
    1.02
    ifiable
    1.01
    ivable
    1.01
    isible
    1.01
    Activations Density 0.331%

    No Known Activations