© 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. 9-RES-JB
    11. 9844
    Prev
    Next
    INDEX
    Explanations

    video-related commands or requests

    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 @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledged
    -0.77
    ItemTracker
    -0.74
    afort
    -0.68
     reusable
    -0.66
    nir
    -0.63
     knowledge
    -0.63
    ©¶æ¥µ
    -0.62
    endered
    -0.62
    needed
    -0.60
    wealth
    -0.59
    POSITIVE LOGITS
     unfold
    1.58
     videos
    1.11
     VIDEOS
    1.05
     replay
    1.04
     Videos
    0.98
     closely
    0.98
     movies
    0.96
     films
    0.94
     documentaries
    0.94
     tapes
    0.93
    Activations Density 0.208%

    No Known Activations