© 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. 16088
    Prev
    Next
    INDEX
    Explanations

    references to actions involving conflict or confrontation

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents and their implications

    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
     his
    -0.61
    his
    -0.60
     their
    -0.55
     HIS
    -0.55
     inexper
    -0.52
     intended
    -0.52
     herself
    -0.52
     thy
    -0.51
     lest
    -0.51
    illary
    -0.51
    POSITIVE LOGITS
    ãĤ¼ãĤ¦ãĤ¹
    0.70
    Ñı
    0.66
    Lots
    0.65
    æĺ¯
    0.64
    Category
    0.59
    "}],"
    0.59
    ãĥ´ãĤ¡
    0.57
    \/\/
    0.57
    Ò
    0.56
    ocaly
    0.56
    Activations Density 0.829%

    No Known Activations