© 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. 14129
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events being initiated or caused by specific entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "With" or indicate a condition or accompanying state

    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
    embed
    -0.91
    insula
    -0.82
    Enlarge
    -0.80
    soType
    -0.76
    Side
    -0.73
    Flickr
    -0.72
    Definition
    -0.71
    onian
    -0.71
    desktop
    -0.71
    orp
    -0.70
    POSITIVE LOGITS
     plenty
    1.11
     injuries
    1.02
     ample
    0.92
     Antonio
    0.91
     Trevor
    0.91
     fewer
    0.90
     suspensions
    0.87
     Marcus
    0.86
     Andre
    0.86
     Giov
    0.86
    Activations Density 0.127%

    No Known Activations