© 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. 2-RES-JB
    11. 8343
    Prev
    Next
    INDEX
    Explanations

    video-related keywords

    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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aunder
    -0.74
    oscope
    -0.72
    ismo
    -0.70
    akedown
    -0.70
    leans
    -0.70
    abil
    -0.70
    sole
    -0.69
    ignt
    -0.69
    avement
    -0.67
    vironment
    -0.66
    POSITIVE LOGITS
     Video
    1.00
    Video
    0.98
     Thumbnails
    0.93
    Player
    0.88
     Videos
    0.84
     Recording
    0.83
    ILLE
    0.83
     Clip
    0.80
    Capture
    0.80
    Audio
    0.79
    Activations Density 0.018%

    No Known Activations