© 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. 2790
    Prev
    Next
    INDEX
    Explanations

    phrases related to reviews or evaluations, particularly highlighting positive aspects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe performance or impact in various contexts, including sports and entertainment

    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
    ò
    -0.81
    tal
    -0.79
     conflic
    -0.77
     unnecess
    -0.76
    aditional
    -0.75
    ilial
    -0.75
     metic
    -0.75
    oreAnd
    -0.75
    ij士
    -0.74
    ñ
    -0.74
    POSITIVE LOGITS
     Koen
    0.68
     Ren
    0.64
     node
    0.63
     Starr
    0.60
     episode
    0.59
    Node
    0.59
     ï
    0.59
     isEnabled
    0.59
     Mayo
    0.58
     Reese
    0.58
    Activations Density 0.181%

    No Known Activations