© 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. 6-RES-JB
    11. 395
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant or memorable event in a personal context

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotions or significant events

    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
    arta
    -1.12
    currently
    -0.78
    ç¥ŀ
    -0.77
    quartered
    -0.74
    Introduced
    -0.73
    avorite
    -0.72
    pta
    -0.68
    mult
    -0.68
    é¾į
    -0.67
    onduct
    -0.67
    POSITIVE LOGITS
     raining
    1.20
     downhill
    0.92
     uphill
    0.84
     impossible
    0.77
     coincidence
    0.74
     spur
    0.73
     surreal
    0.72
     pointless
    0.71
     unintentional
    0.69
     fitting
    0.68
    Activations Density 0.439%

    No Known Activations