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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 226
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversial issues and news events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to criticism or controversy surrounding public figures or actions

    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
    arger
    -0.68
     skelet
    -0.65
    âķIJ
    -0.64
     <[
    -0.63
    theless
    -0.62
     nerv
    -0.61
     pse
    -0.61
     :=
    -0.61
     anecd
    -0.59
    âĹ¼
    -0.56
    POSITIVE LOGITS
     âĢİ
    0.69
    20439
    0.67
    âĢİ
    0.65
     [âĢ¦]
    0.64
     Belfast
    0.61
    î
    0.58
    Brexit
    0.56
    $.
    0.55
     ....
    0.55
    hello
    0.53
    Activations Density 3.644%

    No Known Activations