© 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. 6-RES-JB
    11. 9608
    Prev
    Next
    INDEX
    Explanations

    positive adjectives or phrases indicating benefits or advantages

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating positive outcomes or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iper
    -0.73
    Downloadha
    -0.72
    eters
    -0.70
    racuse
    -0.68
    opers
    -0.67
    pter
    -0.66
    illon
    -0.65
    Bow
    -0.64
    asket
    -0.63
    hyde
    -0.63
    POSITIVE LOGITS
     enough
    1.16
    enough
    1.08
     Enough
    0.83
    bye
    0.82
     nat
    0.80
     karma
    0.77
     optics
    0.72
     additions
    0.70
     news
    0.70
     surpr
    0.70
    Activations Density 0.124%

    No Known Activations