© 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. 8-RES-JB
    11. 19312
    Prev
    Next
    INDEX
    Explanations

    phrases related to impactful or memorable experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express strong emotional reactions or impactful statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     starve
    -0.79
     latitude
    -0.69
    clusive
    -0.69
    iphate
    -0.64
    itives
    -0.63
    anners
    -0.62
     overseen
    -0.61
     prosper
    -0.60
    pmwiki
    -0.60
    ocr
    -0.60
    POSITIVE LOGITS
     me
    0.78
     enthusi
    0.76
     nerves
    0.74
    soType
    0.72
     nerve
    0.71
     Tuls
    0.70
     Saban
    0.65
     Vaugh
    0.64
     Weir
    0.63
     retrospect
    0.63
    Activations Density 0.389%

    No Known Activations