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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 1981
    Prev
    Next
    INDEX
    Explanations

    footage-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of video footage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isner
    -0.81
    gener
    -0.73
    witch
    -0.71
    riend
    -0.66
     SERV
    -0.66
     hast
    -0.64
     specializing
    -0.63
     incre
    -0.63
     âī¤
    -0.63
    weak
    -0.61
    POSITIVE LOGITS
     footage
    3.84
     clips
    1.95
     CCTV
    1.78
     videos
    1.74
     video
    1.62
     filming
    1.54
     filmed
    1.54
     photographs
    1.52
     recordings
    1.51
     clip
    1.51
    Activations Density 0.016%

    No Known Activations