© 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. 10-RES-JB
    11. 11175
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussion or argumentation

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to ethics and morality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soon
    -0.60
    âĦ¢
    -0.55
     âĢİ
    -0.55
    iasco
    -0.54
    Sadly
    -0.54
    forums
    -0.50
     Alas
    -0.49
    FAQ
    -0.49
    wild
    -0.49
    Offline
    -0.49
    POSITIVE LOGITS
     sidx
    0.57
     refere
    0.57
    itialized
    0.55
    tains
    0.54
     attachment
    0.50
     preference
    0.49
     initi
    0.49
     counterpart
    0.49
    tained
    0.49
     assists
    0.48
    Activations Density 0.885%

    No Known Activations