© 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. 6-RES-JB
    11. 7844
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to works or entities that serve as a foundation or inspiration for creations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ownership and adaptations of works

    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
    licks
    -0.72
    assian
    -0.68
    tra
    -0.65
    posure
    -0.64
    aura
    -0.63
    ggles
    -0.62
    ugal
    -0.61
     storms
    -0.61
    tro
    -0.61
     spills
    -0.60
    POSITIVE LOGITS
    actionDate
    0.85
    ertodd
    0.79
    ãĤ´
    0.78
     principally
    0.77
     geographically
    0.77
    HAEL
    0.72
     chiefly
    0.70
    ĸļ
    0.70
    unct
    0.68
    inet
    0.66
    Activations Density 0.211%

    No Known Activations