© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11204
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a longstanding association or characteristic

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of continuity or persistence over time

    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
    regate
    -0.74
    Days
    -0.72
    enary
    -0.68
    illions
    -0.67
    Length
    -0.67
    Pages
    -0.66
    now
    -0.66
    Initial
    -0.65
    illion
    -0.65
    soon
    -0.65
    POSITIVE LOGITS
     regarded
    0.91
     fascinated
    0.91
     shrouded
    0.79
     doubted
    0.77
     uneasy
    0.76
     considered
    0.74
     touted
    0.73
    pired
    0.72
     associated
    0.71
     pegged
    0.70
    Activations Density 0.092%

    No Known Activations