© 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. 10-RES-JB
    11. 5368
    Prev
    Next
    INDEX
    Explanations

    phrases related to events concluding or transitioning to new phases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sequences or components of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arta
    -0.76
    umat
    -0.69
    seless
    -0.68
    tein
    -0.66
    urden
    -0.63
    wrong
    -0.63
     risked
    -0.61
    ãĥ³ãĤ¸
    -0.61
     behaved
    -0.60
    cience
    -0.60
    POSITIVE LOGITS
     announcements
    1.16
     fireworks
    1.01
     another
    0.96
     introdu
    0.91
     sporadic
    0.90
     revelations
    0.89
     explosions
    0.89
     riots
    0.86
     bouts
    0.86
     a
    0.85
    Activations Density 0.288%

    No Known Activations