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

    Neuronpedia

    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. 2-RES-JB
    11. 17611
    Prev
    Next
    INDEX
    Explanations

    phrases related to frames or framing

    oai_token-act-pair · gpt-3.5-turbo

    references to camera frame sizes and types in film or photography

    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
    iott
    -0.80
    withstanding
    -0.78
    itable
    -0.78
    iant
    -0.77
    icably
    -0.76
    ulla
    -0.74
    zai
    -0.72
    inse
    -0.71
    inen
    -0.71
    IUM
    -0.71
    POSITIVE LOGITS
     frames
    1.11
    buffer
    1.04
     Frames
    1.04
     frame
    0.97
     Frame
    0.96
    border
    0.89
    frames
    0.84
    Frames
    0.81
    ////////////////////////////////
    0.78
    Frame
    0.76
    Activations Density 0.008%

    No Known Activations