© 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. 15718
    Prev
    Next
    INDEX
    Explanations

    phrases indicating missed opportunities or alternate scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hypothetical situations and outcomes

    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
     Deb
    -0.63
     Brach
    -0.63
    thus
    -0.61
    ftime
    -0.59
    verend
    -0.59
    Must
    -0.58
    most
    -0.58
    currently
    -0.58
    tainment
    -0.57
    ennett
    -0.57
    POSITIVE LOGITS
     spared
    0.84
     avoided
    0.82
     prevented
    0.78
     born
    0.76
    wolves
    0.75
     invented
    0.74
     saved
    0.74
     sooner
    0.74
     worse
    0.73
    hes
    0.73
    Activations Density 0.095%

    No Known Activations