© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 11472
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional states or experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional experiences and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -0.90
     Router
    -0.84
     Printing
    -0.76
    Maker
    -0.71
    pling
    -0.70
     Maker
    -0.66
     Lic
    -0.66
     Specifications
    -0.65
    lords
    -0.65
     Laun
    -0.65
    POSITIVE LOGITS
     emotional
    3.39
     emotionally
    2.41
     emotion
    2.20
     emotions
    2.07
     sentimental
    1.75
     psychological
    1.68
     emot
    1.58
    otional
    1.44
     empathy
    1.40
     interpersonal
    1.34
    Activations Density 0.027%

    No Known Activations