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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23331
    Prev
    Next
    INDEX
    Explanations

    dates and events associated with specific actions or publications

    oai_token-act-pair · gpt-3.5-turbo

    actions related to publishing or sharing information

    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
    Fit
    -0.66
    assian
    -0.66
    ggles
    -0.61
     stripes
    -0.60
    apers
    -0.60
     Sierra
    -0.59
     gri
    -0.59
    depending
    -0.58
     Cups
    -0.58
     stripe
    -0.57
    POSITIVE LOGITS
     unanimously
    1.00
     by
    0.92
     aback
    0.90
     yesterday
    0.80
     extensively
    0.72
     earlier
    0.69
     briefly
    0.68
    inet
    0.68
    terday
    0.68
     shortly
    0.67
    Activations Density 0.296%

    No Known Activations