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. 19689
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of freedom

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "free" in various contexts

    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
     Ancients
    -0.73
     Everywhere
    -0.73
     Takeru
    -0.71
     Conrad
    -0.70
    BuyableInstoreAndOnline
    -0.70
     Authority
    -0.70
     Io
    -0.69
     Prohibition
    -0.67
    ç¥ŀ
    -0.66
     Archdemon
    -0.65
    POSITIVE LOGITS
    ety
    1.01
    bies
    0.97
    eways
    0.95
    ck
    0.94
    ighter
    0.94
    estyle
    0.94
    natureconservancy
    0.94
    eport
    0.93
    eware
    0.93
     fre
    0.89
    Activations Density 0.007%

    No Known Activations