© 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. 6-RES-JB
    11. 11591
    Prev
    Next
    INDEX
    Explanations

    the phrase "subscribing" and related text indicating a successful or failed subscription action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription confirmations and thank-you notes

    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
     Grayson
    -0.68
     Basil
    -0.67
     Bulgar
    -0.66
     hardness
    -0.63
    ouf
    -0.62
     Dull
    -0.60
     Trent
    -0.60
    icum
    -0.59
     Ort
    -0.59
     brush
    -0.59
    POSITIVE LOGITS
    ãģı
    0.79
    interstitial
    0.76
    Sorry
    0.73
    à¤
    0.69
    ãĤĤ
    0.67
     Please
    0.66
    asse
    0.65
     unlocks
    0.64
     ç¥ŀ
    0.64
    arations
    0.63
    Activations Density 0.038%

    No Known Activations