© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 7781
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong opinions or criticism

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing strong opinions or criticisms about decisions and events

    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
    enhagen
    -0.76
    toggle
    -0.72
    electric
    -0.70
    aceae
    -0.70
     Variable
    -0.70
     clustered
    -0.69
    Enlarge
    -0.67
     Puzzles
    -0.65
     directional
    -0.65
     Inventory
    -0.63
    POSITIVE LOGITS
     disgrace
    1.40
     unacceptable
    1.23
     despicable
    1.23
     irresponsible
    1.19
     tarn
    1.18
     disrespect
    1.18
     shame
    1.17
     dishon
    1.12
     Shame
    1.12
     intolerable
    1.10
    Activations Density 1.154%

    No Known Activations