© 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. 8-RES-JB
    11. 1124
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions or judgments

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating opinions or beliefs about situations

    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
    luaj
    -0.84
    Finish
    -0.72
    igraph
    -0.69
    bies
    -0.67
    iatus
    -0.66
    dies
    -0.65
    upt
    -0.65
    ventures
    -0.65
    undreds
    -0.64
    enary
    -0.62
    POSITIVE LOGITS
     ironic
    1.03
     therefore
    0.99
     understandable
    0.95
     sad
    0.93
     certainly
    0.92
     imperative
    0.91
     obvious
    0.90
     unfortunate
    0.89
     undeniable
    0.89
     inex
    0.88
    Activations Density 0.324%

    No Known Activations