© 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. 7-RES-JB
    11. 1669
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases with emotional or impactful words

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express strong emotional responses or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iaries
    -0.80
    catentry
    -0.79
    abase
    -0.78
    icter
    -0.76
     inexper
    -0.75
    iencies
    -0.74
    iary
    -0.72
     defic
    -0.72
    udget
    -0.70
     regress
    -0.68
    POSITIVE LOGITS
     shouted
    1.08
     chanted
    1.01
     chants
    0.97
     chant
    0.95
     screamed
    0.94
     yelled
    0.94
     lyrics
    0.92
     roared
    0.91
    verbs
    0.88
     slogan
    0.87
    Activations Density 0.719%

    No Known Activations