© 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. 13417
    Prev
    Next
    INDEX
    Explanations

    specific targets or goals mentioned within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to targets in various contexts, particularly in discussions about objectives or subjects of actions

    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
    fo
    -0.76
    iHUD
    -0.72
    loo
    -0.72
    IGH
    -0.65
    ISTORY
    -0.65
    cia
    -0.64
    Champ
    -0.63
    john
    -0.63
    yg
    -0.63
     Expedition
    -0.63
    POSITIVE LOGITS
    ted
    1.39
    ting
    1.01
     audience
    0.89
    eers
    0.78
    ched
    0.77
     demographic
    0.75
     audiences
    0.72
     targets
    0.71
    oided
    0.68
    ivity
    0.66
    Activations Density 0.060%

    No Known Activations