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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 19257
    Prev
    Next
    INDEX
    Explanations

    experiences or instances of a particular event or feeling

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "experienced."

    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
    hatt
    -0.84
    uzzle
    -0.77
    corn
    -0.77
    law
    -0.75
    ococ
    -0.73
    vous
    -0.72
    appa
    -0.72
    ect
    -0.69
    cott
    -0.68
    imov
    -0.68
    POSITIVE LOGITS
    ienced
    0.95
    HAEL
    0.84
     experiences
    0.79
     Experience
    0.76
     experienced
    0.74
     firsthand
    0.73
     experience
    0.71
     veter
    0.71
    OWS
    0.71
    Experience
    0.70
    Activations Density 0.019%

    No Known Activations