© 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. 7-RES-JB
    11. 12521
    Prev
    Next
    INDEX
    Explanations

    phrases related to attention and focus

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance of paying attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.72
    byn
    -0.71
    iHUD
    -0.68
    rie
    -0.66
    \\\\\\\\
    -0.63
    anus
    -0.62
    apeshifter
    -0.61
    lua
    -0.60
    geries
    -0.60
     prohib
    -0.59
    POSITIVE LOGITS
     attent
    0.86
    olescent
    0.74
    é¾įå¥ij士
    0.72
    ibilities
    0.67
    fulness
    0.64
    stakes
    0.63
    mast
    0.63
    ibility
    0.63
    itored
    0.62
     elsewhere
    0.62
    Activations Density 0.023%

    No Known Activations