© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3385
    Prev
    Next
    INDEX
    Explanations

    phrases related to beliefs, opinions, and support for different causes or candidates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to belief and support for individuals or causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.69
    usp
    -0.66
    imgur
    -0.65
    tnc
    -0.60
    spection
    -0.59
    Studio
    -0.59
    escription
    -0.58
    irie
    -0.58
    arthed
    -0.55
    nesota
    -0.55
    POSITIVE LOGITS
     whereas
    1.14
     regardless
    1.10
     but
    1.01
     irrespective
    0.99
     insofar
    0.99
     because
    0.93
     albeit
    0.87
     despite
    0.86
     yes
    0.86
     therefore
    0.85
    Activations Density 0.331%

    No Known Activations