© 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. 21112
    Prev
    Next
    INDEX
    Explanations

    video-related terms and instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to videos and visual media content

    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
    knife
    -0.62
     thro
    -0.62
     manif
    -0.60
     streng
    -0.56
     mosqu
    -0.56
     metab
    -0.56
     polyg
    -0.54
     bis
    -0.54
     fabrication
    -0.53
    igham
    -0.53
    POSITIVE LOGITS
     Thumbnails
    0.76
     ...
    0.66
     Videos
    0.65
    icating
    0.65
     Continue
    0.64
    ...]
    0.64
    available
    0.64
    onder
    0.63
    isites
    0.61
    ]}
    0.61
    Activations Density 0.031%

    No Known Activations