© 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. 3688
    Prev
    Next
    INDEX
    Explanations

    terms related to tasks or actions, particularly involving responsibilities or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that list or include multiple items or topics

    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
    mare
    -0.63
    igers
    -0.58
     Defeat
    -0.57
     Wildcats
    -0.57
    olate
    -0.55
    cium
    -0.55
     Hanna
    -0.54
    cca
    -0.54
    ventory
    -0.53
    bilt
    -0.53
    POSITIVE LOGITS
     uh
    0.90
    among
    0.82
    Æ
    0.76
    appropriately
    0.74
     um
    0.71
     ah
    0.66
    wait
    0.65
     "â̦
    0.65
    mun
    0.64
    advertising
    0.64
    Activations Density 0.273%

    No Known Activations