© 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. 2-RES-JB
    11. 23661
    Prev
    Next
    INDEX
    Explanations

    adjectives related to being twisted or distorted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "twisted," "warped," and related terms indicating distortion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alty
    -0.86
    abet
    -0.85
    ciation
    -0.84
    ¯¯¯¯
    -0.76
    ILA
    -0.74
    worthiness
    -0.73
    cial
    -0.72
    igraph
    -0.71
    cially
    -0.71
    gat
    -0.70
    POSITIVE LOGITS
     twisted
    1.05
     twist
    0.94
     twisting
    0.93
     twists
    0.81
     Twisted
    0.77
     adolesc
    0.76
     Hollow
    0.74
     lengths
    0.73
     imagin
    0.70
     intertw
    0.69
    Activations Density 0.020%

    No Known Activations