© 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. 18637
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating the relationship between entities or conditions

    oai_token-act-pair · gpt-3.5-turbo

    constructions that indicate conditional or situational relationships

    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
    apt
    -0.78
    ve
    -0.75
     Mayo
    -0.74
    tops
    -0.72
    bi
    -0.71
    orde
    -0.71
    ten
    -0.71
    ese
    -0.70
    Sharp
    -0.69
    aldi
    -0.68
    POSITIVE LOGITS
    soever
    1.37
     whereby
    1.12
     wherein
    0.96
    £ı
    0.86
     nomine
    0.80
    iculty
    0.80
    xual
    0.79
     attm
    0.79
     involves
    0.79
    terness
    0.77
    Activations Density 0.004%

    No Known Activations