© 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. 6-RES-JB
    11. 7998
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I was like" which indicates reactions or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atform
    -0.77
    ourse
    -0.75
    Published
    -0.74
    ribution
    -0.74
    apers
    -0.69
    glas
    -0.68
    ulty
    -0.68
    omsky
    -0.66
    wordpress
    -0.66
    iere
    -0.66
    POSITIVE LOGITS
    lihood
    1.04
    liest
    0.88
    lier
    0.82
     wow
    0.79
     crazy
    0.77
    liness
    0.67
     clock
    0.66
     crap
    0.65
     minded
    0.65
     Crazy
    0.63
    Activations Density 0.054%

    No Known Activations