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

    Neuronpedia

    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. 9-RES-JB
    11. 8857
    Prev
    Next
    INDEX
    Explanations

    terms related to official titles or organizations

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and abbreviations related to organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.82
     unison
    -0.76
     blanket
    -0.73
     ripple
    -0.69
     hindsight
    -0.68
     Ogre
    -0.68
     stride
    -0.67
     shutter
    -0.66
     goblins
    -0.66
     fools
    -0.66
    POSITIVE LOGITS
    icultural
    1.10
    istries
    1.05
    ilitation
    1.05
    Services
    1.02
    ensing
    1.01
    onnaissance
    0.99
    ciplinary
    0.99
    abulary
    0.98
    iculture
    0.98
    iciency
    0.97
    Activations Density 0.214%

    No Known Activations