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. 13120
    Prev
    Next
    INDEX
    Explanations

    words related to quantity and events or practices in an organized group or community

    oai_token-act-pair · gpt-3.5-turbo

    phrases conveying substantial value or importance

    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
    ãģ¾
    -0.58
    SPONSORED
    -0.57
    DCS
    -0.56
    Ħ¢
    -0.54
    icted
    -0.51
     ])
    -0.50
    Semitism
    -0.50
    >]
    -0.50
    apo
    -0.49
    OTUS
    -0.49
    POSITIVE LOGITS
    veland
    0.54
    adj
    0.48
    ometimes
    0.48
     however
    0.48
     though
    0.46
    -,
    0.46
     fascinating
    0.44
     modular
    0.44
     alot
    0.43
     Panasonic
    0.43
    Activations Density 2.623%

    No Known Activations