© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 17723
    Prev
    Next
    INDEX
    Explanations

    video-related commands or calls to action

    oai_token-act-pair · gpt-3.5-turbo

    references to videos and watching content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nir
    -0.83
    ledged
    -0.79
    ©¶æ¥µ
    -0.78
    ItemTracker
    -0.74
    afort
    -0.69
    Ĥİ
    -0.65
    ento
    -0.65
     reusable
    -0.64
    Ħ¢
    -0.62
     forgiven
    -0.62
    POSITIVE LOGITS
     unfold
    1.45
     replay
    1.07
     videos
    1.04
     closely
    0.96
     tapes
    0.94
    ideos
    0.94
     VIDEOS
    0.93
     clip
    0.92
     video
    0.92
     clips
    0.90
    Activations Density 0.160%

    No Known Activations