© 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. 6-RES-JB
    11. 1670
    Prev
    Next
    INDEX
    Explanations

    keywords related to attention, focus, and detail

    oai_token-act-pair · gpt-3.5-turbo

    references to attention and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     halves
    -0.71
     Tale
    -0.65
     Yugoslavia
    -0.64
     Pist
    -0.64
     Recon
    -0.64
    tto
    -0.63
     Rouge
    -0.61
    tre
    -0.61
     Dani
    -0.60
     Mehran
    -0.60
    POSITIVE LOGITS
    estinal
    0.93
    orial
    0.89
     attention
    0.84
    ively
    0.82
     spans
    0.78
     Attention
    0.76
     largeDownload
    0.75
    arios
    0.75
     seeker
    0.75
     span
    0.71
    Activations Density 0.023%

    No Known Activations