© 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. 2-RES-JB
    11. 22553
    Prev
    Next
    INDEX
    Explanations

    abbreviations related to technology and updates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific models or teams related to racing or competitive events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leck
    -0.83
    ablishment
    -0.77
     Samoa
    -0.76
    Austral
    -0.75
    iano
    -0.74
     Samar
    -0.74
    anza
    -0.73
    ously
    -0.73
    ificant
    -0.73
    ãĥ¼ãĥĨ
    -0.72
    POSITIVE LOGITS
     RC
    0.98
    ategory
    0.86
    cffff
    0.85
    avorite
    0.83
     mathemat
    0.81
    ©¶æ¥µ
    0.73
    ¥ŀ
    0.71
    conservancy
    0.71
     satell
    0.71
    ²¾
    0.70
    Activations Density 0.008%

    No Known Activations