© 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. 11-RES-JB
    11. 2835
    Prev
    Next
    INDEX
    Explanations

    instances of formatted text that might contain special characters or annotations like 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numerical dates or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uncond
    -0.70
     fug
    -0.69
     swat
    -0.69
     inactive
    -0.69
     prosec
    -0.68
     imperson
    -0.67
     answ
    -0.66
     stacks
    -0.65
     exha
    -0.65
     allied
    -0.65
    POSITIVE LOGITS
    Posted
    1.41
    ³³³³³³³³³³³³³³³³
    1.28
    ³³³³³³³³
    1.28
    posted
    1.27
    ³³³
    1.25
    Synopsis
    1.24
    ³³³³
    1.21
    ³³
    1.19
    Introduction
    1.18
    Born
    1.15
    Activations Density 0.254%

    No Known Activations