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. 12697
    Prev
    Next
    INDEX
    Explanations

    quantitative values with a range up to 10

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate limits or maximum quantities

    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
    cat
    -0.68
    Moving
    -0.68
     doesnt
    -0.68
    Still
    -0.64
    Dro
    -0.63
    rog
    -0.59
    tions
    -0.59
    Creat
    -0.58
    rollers
    -0.58
    brook
    -0.58
    POSITIVE LOGITS
     2024
    0.81
    thirds
    0.79
    pload
    0.79
     200
    0.78
    capacity
    0.78
     2030
    0.77
     150
    0.74
     300
    0.74
     3000
    0.73
    assetsadobe
    0.72
    Activations Density 0.039%

    No Known Activations