© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1839
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical values within a text

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and dates related to events or statistics

    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
    stakes
    -0.58
    76561
    -0.58
    EStream
    -0.57
    é¾į
    -0.57
     sociop
    -0.57
    jen
    -0.57
     satur
    -0.56
     kidneys
    -0.56
    lehem
    -0.56
     reinvest
    -0.55
    POSITIVE LOGITS
    uther
    0.70
    orry
    0.66
    ooks
    0.65
    obia
    0.63
    PC
    0.63
    Mesh
    0.62
    bt
    0.61
    fm
    0.61
    oba
    0.61
     Shock
    0.60
    Activations Density 0.316%

    No Known Activations