© 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. 4-RES-JB
    11. 10415
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name or word "Att" with varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    references to "attachment" in various contexts, particularly relating to emotions and relationships

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

    No Comments

    Negative Logits
    FTWARE
    -0.83
    enegger
    -0.81
    theless
    -0.81
    ORGE
    -0.75
    vous
    -0.74
    ktop
    -0.73
     Cuomo
    -0.72
    beard
    -0.69
    assetsadobe
    -0.69
     Giuliani
    -0.68
    POSITIVE LOGITS
    itudes
    1.24
    ributed
    1.22
    ributes
    1.21
    ention
    1.19
    achment
    1.18
    ainment
    1.18
    itude
    1.17
    ension
    1.17
    orneys
    1.15
    anooga
    1.14
    Activations Density 0.012%

    No Known Activations