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. 10915
    Prev
    Next
    INDEX
    Explanations

    locations or places outside buildings or establishments

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or events occurring outside

    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
    Percent
    -0.74
    oleon
    -0.72
    oka
    -0.72
    XX
    -0.71
    olk
    -0.69
    Lay
    -0.66
    information
    -0.63
    uncle
    -0.63
    lda
    -0.63
    orah
    -0.63
    POSITIVE LOGITS
     patio
    0.74
    ModLoader
    0.70
     Indies
    0.68
    perty
    0.67
    ntil
    0.67
     Stamford
    0.66
     undermin
    0.64
    eatures
    0.63
     adolesc
    0.63
     enclosure
    0.62
    Activations Density 0.021%

    No Known Activations