© 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. 6-RES-JB
    11. 9967
    Prev
    Next
    INDEX
    Explanations

    technology and processes

    oai_token-act-pair · gpt-3.5-turbo

    nouns and verbs related to processes and practices in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guilty
    -0.76
     Parables
    -0.70
    £ı
    -0.66
     Mechdragon
    -0.65
    é¾į
    -0.63
     Defin
    -0.62
     Mous
    -0.59
     Klu
    -0.59
     Prosecut
    -0.55
     guiActiveUnfocused
    -0.53
    POSITIVE LOGITS
     etc
    0.79
    cussion
    0.60
    legram
    0.59
    essment
    0.59
    ibles
    0.58
    etc
    0.57
    ãĥ¼
    0.57
     istg
    0.57
    rites
    0.55
    tal
    0.55
    Activations Density 0.418%

    No Known Activations