© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14287
    Prev
    Next
    INDEX
    Explanations

    references to the handling of various situations or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to how various situations or cases are managed or dealt with

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grade
    -0.68
    atory
    -0.65
     recomm
    -0.64
    addon
    -0.63
    raid
    -0.62
    urt
    -0.62
    intel
    -0.61
    rise
    -0.60
    mare
    -0.60
    azi
    -0.60
    POSITIVE LOGITS
     handled
    1.03
    terness
    0.87
    bars
    0.83
    20439
    0.83
    MpServer
    0.81
     handles
    0.81
     pione
    0.78
     Pradesh
    0.77
    ãĥ¼ãĤ¯
    0.76
    ãĤĮ
    0.74
    Activations Density 0.009%

    No Known Activations