© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16411
    Prev
    Next
    INDEX
    Explanations

    phrases related to hygiene and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to scientific and technical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HCR
    -0.74
    SPONSORED
    -0.73
    iage
    -0.72
    çĦ
    -0.71
    xxxxxxxx
    -0.66
    âĨij
    -0.66
     unaffected
    -0.66
    cember
    -0.66
    ongyang
    -0.65
     basis
    -0.62
    POSITIVE LOGITS
    opter
    0.91
    yll
    0.88
    onica
    0.79
    aucas
    0.79
    ulic
    0.78
    atra
    0.75
    olog
    0.73
    enes
    0.71
    etch
    0.70
    nir
    0.69
    Activations Density 0.160%

    No Known Activations