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. 8-RES-JB
    6. 4508
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to size, dimensions, and measurements

    oai_token-act-pair · gpt-3.5-turbo

    the word "size" and related or comparative terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quished
    -0.87
    meet
    -0.82
    ievers
    -0.81
    worker
    -0.76
    iah
    -0.73
    wife
    -0.71
    atican
    -0.71
    zan
    -0.71
    Ws
    -0.71
    Sec
    -0.70
    POSITIVE LOGITS
     sophistication
    1.22
     durability
    1.17
     stature
    1.17
     accuracy
    1.15
     quantity
    1.15
     depth
    1.14
     curv
    1.13
     width
    1.13
     breadth
    1.12
     severity
    1.12
    Activations Density 0.235%

    No Known Activations