Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19029
    Prev
    Next
    INDEX
    Explanations

    real-time information or applications

    oai_token-act-pair · gpt-3.5-turbo

    references to "real-time" concepts or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redit
    -0.85
    urat
    -0.83
    ramid
    -0.81
    udeb
    -0.79
    lain
    -0.78
    erto
    -0.75
    quet
    -0.73
    iverpool
    -0.71
     Loren
    -0.68
    ieties
    -0.68
    POSITIVE LOGITS
    frames
    0.77
     monitoring
    0.77
     PCR
    0.75
    frame
    0.72
     FPS
    0.72
     inacc
    0.72
    motion
    0.71
    aneously
    0.69
     broadcasting
    0.69
    monitor
    0.68
    Activations Density 0.023%

    No Known Activations