© 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. 10284
    Prev
    Next
    INDEX
    Explanations

    comparisons of different technologies or materials based on specific attributes such as efficiency, cost, or performance

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases highlighting advantages or superiority in various contexts

    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
    Ô
    -0.77
    anta
    -0.77
    Iss
    -0.77
    ................................................................
    -0.71
    soon
    -0.71
    Values
    -0.70
    rev
    -0.69
    FontSize
    -0.68
    Beast
    -0.68
    CVE
    -0.67
    POSITIVE LOGITS
     conventional
    1.58
     traditional
    1.56
     ordinary
    1.31
     regular
    1.24
     normal
    1.12
     terrestrial
    1.10
    traditional
    1.10
     standard
    1.08
     existing
    1.04
     classical
    1.03
    Activations Density 0.310%

    No Known Activations