© 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. 7901
    Prev
    Next
    INDEX
    Explanations

    phrases related to attention or focus on specific things or topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to attention and focus in various contexts

    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
     Vend
    -0.65
     behaves
    -0.63
     sued
    -0.61
     basket
    -0.60
     violates
    -0.60
     Chains
    -0.60
     behave
    -0.60
     masterpiece
    -0.60
     baskets
    -0.59
     stacks
    -0.59
    POSITIVE LOGITS
    Ļ½
    0.77
    ij士
    0.76
    ayers
    0.74
    Ī
    0.73
    between
    0.73
    oris
    0.72
    oria
    0.72
    »Ĵ
    0.71
    terness
    0.70
    Policy
    0.70
    Activations Density 0.302%

    No Known Activations