© 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. 3-RES-JB
    11. 9654
    Prev
    Next
    INDEX
    Explanations

    slideshows or montages in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to visual presentations, such as slideshows and infographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alties
    -0.87
    quartered
    -0.86
    alde
    -0.81
    alities
    -0.77
    osponsors
    -0.75
    sterdam
    -0.74
    hood
    -0.74
    ties
    -0.72
    profits
    -0.72
    omin
    -0.72
    POSITIVE LOGITS
     slideshow
    1.12
     mont
    1.06
     chore
    0.78
     recap
    0.72
    ideshow
    0.72
     caption
    0.71
     Cree
    0.68
     img
    0.68
     timer
    0.68
     IMAGES
    0.67
    Activations Density 0.018%

    No Known Activations