© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 837
    Prev
    Next
    INDEX
    Explanations

    verbs describing actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles that describe actions

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

    No Comments

    Negative Logits
    berra
    -0.72
    eus
    -0.68
    taboola
    -0.66
    zip
    -0.65
    iere
    -0.65
    hap
    -0.64
    oba
    -0.64
    Enlarge
    -0.64
    Publisher
    -0.64
    NBC
    -0.63
    POSITIVE LOGITS
     oneself
    0.77
     machines
    0.74
     exha
    0.72
     habits
    0.70
     Machines
    0.69
    HAM
    0.69
    æĸ¹
    0.69
     establishments
    0.67
     alone
    0.66
     Practices
    0.66
    Activations Density 0.298%

    No Known Activations