© 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. 12-RES-JB
    11. 4059
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict or disagreement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to various forms of media, particularly literature and film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    EStream
    -0.90
    PDATE
    -0.84
    Redd
    -0.82
    IFIED
    -0.77
    soType
    -0.77
    Offline
    -0.76
    ModLoader
    -0.72
    Magikarp
    -0.70
    Wallet
    -0.70
    æ°
    -0.69
    POSITIVE LOGITS
     involve
    1.43
     depict
    1.38
     contain
    1.35
     feature
    1.25
     incorporate
    1.22
     rely
    1.21
     focus
    1.21
     hinge
    1.15
     utilize
    1.15
     portray
    1.14
    Activations Density 0.453%

    No Known Activations