© 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. 2-RES-JB
    11. 15471
    Prev
    Next
    INDEX
    Explanations

    references to legal or political terms related to punishment or legislation

    oai_token-act-pair · gpt-3.5-turbo

    references to the death penalty and financial issues related to the debt ceiling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.84
    href
    -0.80
     antioxid
    -0.75
     Modes
    -0.74
    0002
    -0.72
     IDE
    -0.69
    GMT
    -0.69
    é¾įåĸļ士
    -0.67
    Sel
    -0.67
     Particip
    -0.66
    POSITIVE LOGITS
     accus
    0.78
     offic
    0.75
     treadmill
    0.74
     athlet
    0.72
     pageant
    0.72
    mma
    0.70
    ocrine
    0.68
     pounds
    0.68
    hee
    0.68
    emale
    0.67
    Activations Density 0.254%

    No Known Activations