© 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. 11483
    Prev
    Next
    INDEX
    Explanations

    numerical values preceded by the phrase "up to"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to limits or maximums

    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
    Dro
    -0.68
    Reviewer
    -0.63
    åº
    -0.62
    News
    -0.61
    Posted
    -0.61
     doesnt
    -0.60
    Tools
    -0.60
    Moving
    -0.60
    Leave
    -0.59
    Still
    -0.59
    POSITIVE LOGITS
     150
    1.05
     200
    1.01
     300
    0.97
     100
    0.97
     500
    0.95
     400
    0.95
     80
    0.94
     3000
    0.94
     1500
    0.94
     50
    0.94
    Activations Density 0.043%

    No Known Activations