© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12887
    Prev
    Next
    INDEX
    Explanations

    email-related actions and updates

    oai_token-act-pair · gpt-3.5-turbo

    references to actions related to sharing or forwarding content

    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
     sol
    -0.77
     pressure
    -0.76
     shock
    -0.75
     disapp
    -0.72
     resilient
    -0.72
     fullest
    -0.72
     outsiders
    -0.71
     predict
    -0.71
     dens
    -0.71
     compromise
    -0.71
    POSITIVE LOGITS
     Ago
    1.22
     Below
    1.12
     About
    1.11
     Than
    1.09
     Own
    1.04
     Include
    1.04
     Form
    1.01
     Content
    0.99
     Definition
    0.97
     Latest
    0.96
    Activations Density 0.121%

    No Known Activations