© 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. 3124
    Prev
    Next
    INDEX
    Explanations

    phrases related to performing actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to specific actions or occurrences

    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
    usha
    -0.69
    inventoryQuantity
    -0.68
    edia
    -0.67
     boards
    -0.67
    ovi
    -0.65
    IDES
    -0.65
    éŃĶ
    -0.64
    izons
    -0.62
    ãĥ¼ãĥ³
    -0.62
    hner
    -0.62
    POSITIVE LOGITS
     thing
    0.98
     job
    0.92
     kind
    0.85
     deed
    0.82
     stuff
    0.80
     same
    0.79
     unthinkable
    0.79
     trick
    0.78
     sort
    0.78
     anyways
    0.78
    Activations Density 0.052%

    No Known Activations