© 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. 4335
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts where something continues or progresses

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate continuity or persistence

    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
    ãĤ§
    -0.83
    ij士
    -0.77
    ython
    -0.69
    ãĥ¯ãĥ³
    -0.69
    ãĤ©
    -0.65
    ´
    -0.64
    çĶ°
    -0.62
     Choice
    -0.61
    arters
    -0.60
    ulk
    -0.60
    POSITIVE LOGITS
     unab
    0.88
     forever
    0.85
     endlessly
    0.84
     indefinitely
    0.83
    shore
    0.83
     uninterrupted
    0.82
     autop
    0.82
     unnoticed
    0.75
    uph
    0.73
     behalf
    0.70
    Activations Density 0.050%

    No Known Activations