© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4897
    Prev
    Next
    INDEX
    Explanations

    phrases related to worrying or dealing with concerns

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the phrase "worry about."

    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
    hiba
    -0.84
    zynski
    -0.83
    isode
    -0.82
    hesis
    -0.81
    icol
    -0.79
    oun
    -0.77
    hai
    -0.72
    Sport
    -0.72
    Lens
    -0.72
    SPONSORED
    -0.72
    POSITIVE LOGITS
     preserving
    1.01
     protecting
    0.92
     getting
    0.91
     saving
    0.88
     whether
    0.88
     losing
    0.87
     improving
    0.86
     escaping
    0.83
     how
    0.83
     hygiene
    0.83
    Activations Density 0.079%

    No Known Activations