© 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. 11409
    Prev
    Next
    INDEX
    Explanations

    specific formatting patterns with characters

    oai_token-act-pair · gpt-3.5-turbo

    the presence of an end-of-text marker

    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
     eleph
    -0.71
     stressed
    -0.69
     milit
    -0.67
     habit
    -0.67
     retard
    -0.67
     sovereign
    -0.67
     additionally
    -0.66
     bloc
    -0.65
     staunch
    -0.65
     presumptive
    -0.65
    POSITIVE LOGITS
    Synopsis
    1.56
    Description
    1.52
    Reviewer
    1.49
    Introduction
    1.48
    Topic
    1.45
    Overview
    1.45
    Reviewed
    1.44
    Enlarge
    1.43
    Welcome
    1.43
    Offline
    1.38
    Activations Density 0.331%

    No Known Activations