© 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. 3368
    Prev
    Next
    INDEX
    Explanations

    words related to actions or events that have occurred or are currently happening

    oai_token-act-pair · gpt-3.5-turbo

    words indicating possession or ownership

    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
     dump
    -0.62
     subtract
    -0.61
     dot
    -0.60
     bribe
    -0.58
    opian
    -0.58
    acle
    -0.57
     grant
    -0.57
     halt
    -0.56
    onsense
    -0.56
    ancel
    -0.55
    POSITIVE LOGITS
     been
    1.47
    been
    1.34
     gotten
    1.33
     done
    1.21
     Been
    1.19
     gone
    1.05
     undergone
    1.04
     grown
    1.04
     begun
    1.02
     fallen
    1.02
    Activations Density 0.172%

    No Known Activations