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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 1189
    Prev
    Next
    INDEX
    Explanations

    adverbs related to the speed of certain actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "slowly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilion
    -0.91
    ãĥ¤
    -0.87
    features
    -0.81
    tein
    -0.81
    tal
    -0.80
    quickShipAvailable
    -0.77
    Ãį
    -0.70
    eer
    -0.69
     Parables
    -0.69
    rists
    -0.68
    POSITIVE LOGITS
     paced
    0.94
     incre
    0.80
     transitioning
    0.79
     destro
    0.78
     progressing
    0.77
     simmer
    0.76
     starve
    0.76
     trickle
    0.75
     bleed
    0.75
     accelerating
    0.73
    Activations Density 0.007%

    No Known Activations