© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 22159
    Prev
    Next
    INDEX
    Explanations

    news headlines with the word "watch" followed by a video or interview link below

    oai_token-act-pair · gpt-3.5-turbo

    references to multimedia content, specifically videos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disciplines
    -0.77
    ²¾
    -0.76
     literature
    -0.71
     cig
    -0.70
     acron
    -0.69
    abilities
    -0.69
     journals
    -0.69
     notebooks
    -0.67
     numbering
    -0.67
     cakes
    -0.67
    POSITIVE LOGITS
     clip
    1.06
     VIDEO
    0.91
    WATCH
    0.90
    Video
    0.89
     footage
    0.88
     FULL
    0.86
     Trailer
    0.85
     replay
    0.85
     HuffPost
    0.85
     Transcript
    0.84
    Activations Density 0.146%

    No Known Activations