© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 20604
    Prev
    Next
    INDEX
    Explanations

    technology-related terms, such as apps, devices, and games

    oai_token-act-pair · gpt-3.5-turbo

    various types of applications, creative works, and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.77
    atars
    -0.72
    igl
    -0.71
    hner
    -0.70
    ãĥĥãĥī
    -0.69
     Doors
    -0.59
    olars
    -0.58
    ertain
    -0.58
    uckles
    -0.58
    uez
    -0.57
    POSITIVE LOGITS
     Called
    0.72
     called
    0.70
     designed
    0.70
     comprised
    0.70
     marketed
    0.68
     whose
    0.66
     launched
    0.66
     competitor
    0.66
    Id
    0.66
    mable
    0.65
    Activations Density 0.422%

    No Known Activations