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. 0-RES-JB
    6. 19627
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific object - a cookie jar

    oai_token-act-pair · gpt-3.5-turbo

    references to jars

    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
    éĥ
    -0.73
     ECO
    -0.69
     GPS
    -0.68
    åİ
    -0.65
    uro
    -0.64
    ennes
    -0.64
     Belarus
    -0.64
     endurance
    -0.64
     promoters
    -0.63
    termination
    -0.63
    POSITIVE LOGITS
     jar
    3.57
     jars
    3.24
     Jar
    2.77
    Jar
    2.60
    jar
    2.06
     jelly
    1.10
     flask
    1.05
     hive
    0.98
     crate
    0.97
     container
    0.97
    Activations Density 0.017%

    No Known Activations