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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5899
    Prev
    Next
    INDEX
    Explanations

    words related to Greece

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ree"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.93
     Mongolia
    -0.72
     specificity
    -0.70
    inelli
    -0.68
    ancial
    -0.67
    ictive
    -0.66
    ulators
    -0.64
    rift
    -0.64
     Takeru
    -0.63
     Manson
    -0.62
    POSITIVE LOGITS
    pee
    0.98
    pees
    0.94
    bling
    0.89
    ks
    0.89
    ce
    0.86
    cker
    0.85
    bles
    0.84
    glas
    0.84
    llor
    0.79
    ree
    0.79
    Activations Density 0.020%

    No Known Activations