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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20081
    Prev
    Next
    INDEX
    Explanations

    YouTube links

    oai_token-act-pair · gpt-3.5-turbo

    references to YouTube and related URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dull
    -0.75
     Dund
    -0.74
     Greenberg
    -0.70
     Daly
    -0.70
     PTSD
    -0.68
     Leth
    -0.67
     Chau
    -0.66
     Dew
    -0.66
     Sapp
    -0.65
     Jub
    -0.65
    POSITIVE LOGITS
    youtu
    1.28
    youtube
    1.27
     youtube
    1.05
    plays
    0.95
    ideo
    0.91
    ogi
    0.86
    uploads
    0.84
    ileaks
    0.82
    ħĭ
    0.81
    urated
    0.81
    Activations Density 0.008%

    No Known Activations