© 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. 2897
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and interaction between individuals

    oai_token-act-pair · gpt-3.5-turbo

    language related to conflict and accusations

    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
    iasm
    -0.74
    erning
    -0.72
    xtap
    -0.72
    ctory
    -0.69
    ornings
    -0.67
    cour
    -0.65
    ¯¯¯¯¯¯¯¯
    -0.64
    though
    -0.64
    empl
    -0.63
    ayers
    -0.63
    POSITIVE LOGITS
     yours
    0.96
     ..."
    0.94
     âĢ¦"
    0.92
    !'"
    0.91
    âĢ¦"
    0.89
    .'"
    0.88
     ______
    0.86
     ours
    0.84
     somebody
    0.81
    ..."
    0.80
    Activations Density 0.753%

    No Known Activations