© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 5368
    Prev
    Next
    INDEX
    Explanations

    phrases expressing agreement or disagreement with emotional intensity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of disappointment or concern associated with experiences or actions

    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
    pton
    -0.70
     Related
    -0.64
     Industries
    -0.64
    ksh
    -0.64
     CLS
    -0.63
    BN
    -0.63
    SPONSORED
    -0.62
    ICS
    -0.60
    etary
    -0.60
     Speaking
    -0.60
    POSITIVE LOGITS
     impunity
    1.38
     caution
    1.35
     utmost
    1.34
     regard
    1.17
     regards
    1.10
     dignity
    1.09
     certainty
    1.09
     gust
    1.08
     respect
    1.05
     reverence
    1.05
    Activations Density 0.159%

    No Known Activations