© 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. 8-RES-JB
    11. 21749
    Prev
    Next
    INDEX
    Explanations

    negative or critical adjectives

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors and critique-related terms

    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
    Downloadha
    -0.82
    iler
    -0.78
    ologue
    -0.73
    udeb
    -0.70
    rongh
    -0.69
    »Ĵ
    -0.69
    opez
    -0.68
    roma
    -0.68
    hover
    -0.67
    onde
    -0.67
    POSITIVE LOGITS
     enough
    1.14
     territory
    0.84
     insanity
    0.84
     storytelling
    0.83
     folly
    0.82
     nonsense
    0.82
    speak
    0.81
     coincidence
    0.81
     fodder
    0.78
     stupidity
    0.78
    Activations Density 0.359%

    No Known Activations