© 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. 11-RES-JB
    11. 10030
    Prev
    Next
    INDEX
    Explanations

    online video related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to video 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
     sciences
    -0.64
    eton
    -0.63
    anthrop
    -0.61
    verages
    -0.61
    ammy
    -0.60
    earch
    -0.59
    terday
    -0.59
    cember
    -0.59
    esters
    -0.58
     brow
    -0.58
    POSITIVE LOGITS
    duration
    0.68
    bleacher
    0.68
     CLSID
    0.67
     video
    0.63
     trailer
    0.60
    Video
    0.59
    english
    0.59
     Vine
    0.57
     content
    0.55
    video
    0.55
    Activations Density 0.028%

    No Known Activations