© 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. 1-RES-JB
    11. 22416
    Prev
    Next
    INDEX
    Explanations

    words related to subversion or overthrow

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "vert" and its variations, which likely relate to direction or orientation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®éŃĶ
    -0.77
    çĦ
    -0.73
    %"
    -0.68
     Bei
    -0.67
    ãģ®æ
    -0.64
     Kaw
    -0.62
    Pref
    -0.61
    giving
    -0.61
    ãģĤ
    -0.60
    tta
    -0.60
    POSITIVE LOGITS
    vert
    1.24
    ibility
    0.95
    igo
    0.95
    icals
    0.92
    verted
    0.91
    verting
    0.90
    verts
    0.87
    ibilities
    0.87
    iger
    0.86
    ible
    0.85
    Activations Density 0.010%

    No Known Activations