© 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. 6-RES-JB
    11. 9478
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or steps

    oai_token-act-pair · gpt-3.5-turbo

    specific terms and concepts related to instructions, procedures, and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uga
    -0.65
    phia
    -0.61
    arij
    -0.60
    ¿½
    -0.60
    £ı
    -0.60
    agna
    -0.60
    pher
    -0.59
    ģĸ
    -0.59
    pherd
    -0.59
    elvet
    -0.57
    POSITIVE LOGITS
    ickets
    0.66
    itiveness
    0.59
    ById
    0.56
    Cooldown
    0.56
     sqor
    0.55
     Refresh
    0.53
     Craw
    0.52
    Houston
    0.52
     Boulder
    0.50
     Spotify
    0.50
    Activations Density 0.972%

    No Known Activations