© 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. 681
    Prev
    Next
    INDEX
    Explanations

    items or tools that can be interacted with or switched out in a system

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to physical items and infrastructure

    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
    Was
    -0.67
     Was
    -0.66
    Said
    -0.62
     Satanic
    -0.61
    Recomm
    -0.56
     Investigator
    -0.53
    Lear
    -0.52
     Died
    -0.51
     Pieces
    -0.50
    Primary
    -0.50
    POSITIVE LOGITS
     abound
    1.38
     are
    1.35
     aren
    1.29
     tend
    1.21
     seem
    1.21
     have
    1.19
     comprise
    1.17
     remain
    1.15
     embody
    1.13
     thrive
    1.10
    Activations Density 0.546%

    No Known Activations