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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 21890
    Prev
    Next
    INDEX
    Explanations

    phrases related to conducting studies or investigations

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to research and investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    appointed
    -0.81
    anya
    -0.73
    ©¶æ¥µ
    -0.72
    DragonMagazine
    -0.71
    Hon
    -0.70
    ç«
    -0.69
    æł
    -0.68
     slapped
    -0.67
    ãĥ¼ãĥ«
    -0.67
    hon
    -0.66
    POSITIVE LOGITS
     whether
    1.26
     how
    1.22
     correlations
    1.08
     hypotheses
    1.03
     trends
    1.02
     heterogeneity
    1.00
     feasibility
    0.99
     impacts
    0.97
     aspects
    0.95
     why
    0.94
    Activations Density 0.204%

    No Known Activations