Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7355
    Prev
    Next
    INDEX
    Explanations

    phrases related to applying pressure or taking something quickly

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pinch" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opers
    -0.77
    nesty
    -0.74
    laws
    -0.73
    makers
    -0.71
    Elect
    -0.68
    etus
    -0.68
    ãĥ¯
    -0.68
    isher
    -0.67
     Defendants
    -0.67
     Transgender
    -0.67
    POSITIVE LOGITS
     pinch
    4.05
    anced
    0.98
     multit
    0.96
     touch
    0.94
     propri
    0.94
     zoom
    0.87
     fingert
    0.86
     wrench
    0.82
     Ara
    0.78
     Touch
    0.78
    Activations Density 0.030%

    No Known Activations