© 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. 3-RES-JB
    11. 16230
    Prev
    Next
    INDEX
    Explanations

    phrases related to a military context, such as weapons and strategies

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "phase" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olls
    -0.84
    osponsors
    -0.81
    papers
    -0.76
    arious
    -0.70
    iannopoulos
    -0.69
    Bell
    -0.65
    ella
    -0.64
    aught
    -0.64
     provisional
    -0.63
    obb
    -0.63
    POSITIVE LOGITS
    xual
    1.11
     Parenthood
    1.04
    asing
    0.77
    hift
    0.74
     Sap
    0.71
    ased
    0.71
    chwitz
    0.68
    asant
    0.64
    ;;;;;;;;;;;;
    0.64
    lly
    0.63
    Activations Density 0.011%

    No Known Activations