© 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. 7-RES-JB
    11. 2183
    Prev
    Next
    INDEX
    Explanations

    the phrase "think of" followed by various objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the verb "think of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pite
    -0.66
    soever
    -0.63
     subsequ
    -0.62
    Tweet
    -0.60
     proclaimed
    -0.59
    erer
    -0.59
    ante
    -0.57
     asserted
    -0.57
    Found
    -0.57
    ollah
    -0.57
    POSITIVE LOGITS
    èĪ
    0.74
    agine
    0.70
    pheus
    0.68
     externalToEVAOnly
    0.66
     oneself
    0.65
     ourselves
    0.64
    boro
    0.62
    æĺ¯
    0.61
    ¥µ
    0.61
     ways
    0.61
    Activations Density 0.055%

    No Known Activations