© 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 EvalsExportsinterp-engineNEWAPI 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. 3307
    Prev
    Next
    INDEX
    Explanations

    file formats and technological terms related to media and compression

    oai_token-act-pair · gpt-3.5-turbo

    references to digital file formats and their properties

    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
    igil
    -0.87
    ndra
    -0.77
     Scion
    -0.76
     Ascend
    -0.75
     Kier
    -0.74
     Satanic
    -0.69
     inqu
    -0.69
    ä¸ī
    -0.65
     Leilan
    -0.65
    bol
    -0.65
    POSITIVE LOGITS
     MPEG
    1.75
     codec
    1.62
     JPEG
    1.56
    mpeg
    1.53
     subtitles
    1.35
     AAC
    1.31
     playback
    1.31
     encoding
    1.31
     uncomp
    1.30
     PNG
    1.30
    Activations Density 0.395%

    No Known Activations