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. 11062
    Prev
    Next
    INDEX
    Explanations

    phrases related to the city of San Jose and its hockey team, the Sharks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "San Jose"

    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
    atform
    -0.82
    女
    -0.77
    Els
    -0.76
    icles
    -0.75
    ãĤ¤ãĥĪ
    -0.75
    natureconservancy
    -0.74
    ischer
    -0.73
    ICLE
    -0.68
    ickle
    -0.67
    holder
    -0.65
    POSITIVE LOGITS
     Earthqu
    1.07
     Sharks
    0.86
    Ń·
    0.76
     Valley
    0.73
    olean
    0.70
    ricanes
    0.69
    fc
    0.68
    nton
    0.68
    mia
    0.68
    ppa
    0.67
    Activations Density 0.016%

    No Known Activations