© 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. 15739
    Prev
    Next
    INDEX
    Explanations

    phrases related to difficulty, urgency, and consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing difficulty and challenges

    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
     untouched
    -0.56
     excav
    -0.53
     distinctive
    -0.51
     searched
    -0.51
     existed
    -0.51
     assimil
    -0.51
     annot
    -0.50
     extensively
    -0.50
     outper
    -0.50
     underrated
    -0.49
    POSITIVE LOGITS
     consolation
    0.66
     coincidence
    0.64
    ourt
    0.64
    farious
    0.58
     semantics
    0.57
     inev
    0.57
     Pyr
    0.56
     hindsight
    0.56
    ayers
    0.55
    cakes
    0.53
    Activations Density 0.466%

    No Known Activations