© 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. 2047
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions that involve some force or effort

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'y'

    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
     Wonderland
    -0.87
    IUM
    -0.68
    tenance
    -0.67
     PowerPoint
    -0.65
    ULAR
    -0.65
    Oracle
    -0.65
    lessly
    -0.65
    ãĥ´ãĤ¡
    -0.64
     Excellence
    -0.62
    EMENT
    -0.60
    POSITIVE LOGITS
    anked
    1.06
    idd
    1.06
    ahoo
    1.03
    aku
    0.98
    ield
    0.97
    orkshire
    0.96
    ummy
    0.96
    von
    0.95
    onder
    0.93
    ank
    0.93
    Activations Density 0.030%

    No Known Activations