© 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. 9-RES-JB
    11. 10136
    Prev
    Next
    INDEX
    Explanations

    grammar patterns indicating past actions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    instances of emotional complexity in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiName
    -0.72
    TRUMP
    -0.72
     promotes
    -0.71
    agogue
    -0.71
    espie
    -0.71
     Replay
    -0.69
    eware
    -0.69
     demos
    -0.66
    FM
    -0.65
    olphins
    -0.65
    POSITIVE LOGITS
     Jaune
    1.33
     Pyrrha
    1.25
     Malfoy
    1.14
     Severus
    1.13
     Elsa
    1.12
     Weasley
    1.09
     sighed
    1.08
     Snape
    1.07
     Hermione
    1.06
     Dumbledore
    1.01
    Activations Density 0.953%

    No Known Activations