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. 17556
    Prev
    Next
    INDEX
    Explanations

    words related to visual descriptions such as "planned," "waters," "Fukushima," "image," and "showing."

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases involving "of the" and "the" to identify structural elements in descriptions

    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
    lust
    -0.83
    Write
    -0.73
    Tier
    -0.70
     relies
    -0.66
    visory
    -0.66
    ItemTracker
    -0.66
    govtrack
    -0.65
    arten
    -0.65
    Marginal
    -0.65
    Slot
    -0.64
    POSITIVE LOGITS
     underside
    1.09
     aftermath
    1.00
     likeness
    0.96
     devastation
    0.91
    tnc
    0.90
     impending
    0.89
     silhou
    0.88
     skyline
    0.88
     sunrise
    0.86
     silhouette
    0.85
    Activations Density 0.284%

    No Known Activations