© 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. 10741
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or progress

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions related to movement and progression through spaces

    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
    amount
    -0.72
    cia
    -0.67
    Quantity
    -0.65
    anooga
    -0.64
    wrong
    -0.64
    illegal
    -0.62
     Exception
    -0.61
    otally
    -0.61
    anged
    -0.60
    ever
    -0.59
    POSITIVE LOGITS
     checkout
    0.76
     unfolds
    0.74
     progresses
    0.68
     toward
    0.68
     unfold
    0.68
     THR
    0.67
     towards
    0.67
    rily
    0.66
    ggle
    0.66
     progressed
    0.64
    Activations Density 0.209%

    No Known Activations