© 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. 7-RES-JB
    6. 2819
    Prev
    Next
    INDEX
    Explanations

    phrases related to thoughts, understanding, and mental processes

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to planning and progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OUND
    -0.69
    Morning
    -0.60
     endif
    -0.57
    Els
    -0.57
    azon
    -0.56
    Tu
    -0.56
    prim
    -0.56
    ortment
    -0.55
    ARS
    -0.54
    ounding
    -0.53
    POSITIVE LOGITS
     there
    0.77
     we
    0.66
    ,
    0.63
    there
    0.63
    ,.
    0.61
     nobody
    0.59
    tarians
    0.59
    *,
    0.57
     contestants
    0.57
    ,...
    0.57
    Activations Density 0.603%

    No Known Activations