© 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. 11-RES-JB
    11. 20435
    Prev
    Next
    INDEX
    Explanations

    phrases related to narratives or storytelling

    oai_token-act-pair · gpt-3.5-turbo

    references to various cultural narratives or documentaries

    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
    Anyway
    -0.81
     Preferred
    -0.75
     Subst
    -0.71
     crap
    -0.70
    Registered
    -0.70
    Happy
    -0.69
     liability
    -0.69
     spam
    -0.69
     Announce
    -0.66
     Cancel
    -0.65
    POSITIVE LOGITS
     vividly
    1.08
     perspectives
    1.05
     explores
    1.04
     rive
    1.04
     illuminating
    1.03
     intertw
    0.99
     firsthand
    0.99
     insights
    0.99
     interviews
    0.98
     uncover
    0.98
    Activations Density 0.469%

    No Known Activations