© 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 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. 14731
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions of removing or stopping something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dropped" in various contexts

    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
    eway
    -0.78
    eur
    -0.73
    iew
    -0.65
    Storage
    -0.64
    sylv
    -0.63
    iola
    -0.63
     Amen
    -0.62
    rs
    -0.61
    cession
    -0.60
    storage
    -0.59
    POSITIVE LOGITS
     bombshell
    1.15
     hints
    1.08
     bombs
    1.01
     leaflets
    1.01
     jaws
    0.99
     overboard
    0.80
    bomb
    0.80
    kick
    0.77
     acid
    0.77
     dime
    0.77
    Activations Density 0.098%

    No Known Activations