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. 2-RES-JB
    6. 9810
    Prev
    Next
    INDEX
    Explanations

    terms related to the name "Tiny"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "tiny."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulative
    -0.82
    awaru
    -0.78
    consumer
    -0.74
    umers
    -0.73
    tips
    -0.72
    ORN
    -0.71
    lished
    -0.68
    akening
    -0.68
    olkien
    -0.67
    ilitating
    -0.66
    POSITIVE LOGITS
    iny
    0.95
    uania
    0.80
     Caesar
    0.75
    yy
    0.75
    uan
    0.72
     Rhod
    0.70
    oon
    0.66
     Barbarian
    0.65
    RNA
    0.65
    arat
    0.64
    Activations Density 0.009%

    No Known Activations