© 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. 1772
    Prev
    Next
    INDEX
    Explanations

    descriptive words related to emotions and tones

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of emotional depth and authenticity in media content

    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
    Stack
    -0.86
    STEP
    -0.79
    stack
    -0.78
    Solution
    -0.77
    Upgrade
    -0.76
    SEA
    -0.76
    ITNESS
    -0.76
    Spr
    -0.76
    UMP
    -0.74
    GC
    -0.73
    POSITIVE LOGITS
     realism
    1.25
     satire
    1.21
     humor
    1.21
     themes
    1.20
     melanch
    1.18
     storytelling
    1.15
     lyr
    1.14
     melancholy
    1.12
     comedic
    1.11
     scenes
    1.11
    Activations Density 0.500%

    No Known Activations