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. 0-RES-JB
    6. 20792
    Prev
    Next
    INDEX
    Explanations

    terms related to file sizes or storage capacity

    oai_token-act-pair · gpt-3.5-turbo

    metrics related to data storage capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alia
    -0.69
    houses
    -0.68
    forestation
    -0.67
    forward
    -0.65
    cast
    -0.64
    vine
    -0.63
    Wra
    -0.63
    Cos
    -0.62
    wrap
    -0.61
    witch
    -0.61
    POSITIVE LOGITS
     MB
    3.84
    MB
    2.37
     KB
    1.97
     GB
    1.79
    KB
    1.52
     Mb
    1.46
     MBA
    1.44
     TB
    1.41
    mb
    1.39
    GB
    1.35
    Activations Density 0.013%

    No Known Activations