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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 10625
    Prev
    Next
    INDEX
    Explanations

    phrases indicating addition or extra information

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases involving the word "well."

    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
    hip
    -0.75
    rush
    -0.75
    anos
    -0.72
    iolet
    -0.66
    absolute
    -0.66
    mare
    -0.65
    ombo
    -0.64
    terness
    -0.64
    SHIP
    -0.62
    İĭ
    -0.61
    POSITIVE LOGITS
    ________________________________________________________________
    0.70
     suited
    0.68
     behaved
    0.68
     liked
    0.67
    ortment
    0.65
    ãĤ¶
    0.63
    above
    0.63
    FontSize
    0.63
    epad
    0.62
    ×ķ
    0.62
    Activations Density 0.044%

    No Known Activations