© 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 EvalsExportsAPI 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. 4-RES-JB
    11. 4908
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call to action to watch a video

    oai_token-act-pair · gpt-3.5-turbo

    references to videos and related multimedia content

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

    No Comments

    Negative Logits
     academia
    -0.74
     Wonderland
    -0.71
     reconciliation
    -0.68
     Gibbs
    -0.68
    REF
    -0.66
     Aberdeen
    -0.65
     virtue
    -0.65
    sole
    -0.64
     plagiar
    -0.64
     Mole
    -0.64
    POSITIVE LOGITS
     Thumbnails
    1.12
     WATCHED
    1.08
     Videos
    1.02
     VIDEOS
    0.89
    Video
    0.83
    natureconservancy
    0.81
     âĩ
    0.81
    icult
    0.80
    iques
    0.79
     âĢº
    0.78
    Activations Density 0.009%

    No Known Activations