© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8332
    Prev
    Next
    INDEX
    Explanations

    phrases related to coping with or managing difficult situations

    oai_token-act-pair · gpt-3.5-turbo
    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
    ifer
    -0.75
    psey
    -0.75
    asus
    -0.68
    opers
    -0.62
    fil
    -0.61
    fram
    -0.61
    mare
    -0.60
    umer
    -0.60
    si
    -0.60
    ettel
    -0.59
    POSITIVE LOGITS
     deals
    0.90
     trave
    0.79
     dealings
    0.78
     Deals
    0.75
    cohol
    0.71
     Deal
    0.70
     encount
    0.69
    Deal
    0.69
     Jagu
    0.69
    ership
    0.68
    Activations Density 0.026%

    No Known Activations