© 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. 8-RES-JB
    11. 7845
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or entities mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to groups or categories of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.82
    uncture
    -0.73
    itiz
    -0.72
     concess
    -0.67
     landmark
    -0.67
    dose
    -0.67
    ļéĨĴ
    -0.66
    availability
    -0.65
    ilege
    -0.65
    clinton
    -0.65
    POSITIVE LOGITS
     mercenaries
    1.15
     thugs
    1.13
     warriors
    1.12
     bandits
    1.10
    wolves
    1.09
     descendants
    1.08
     anarchists
    1.06
     losers
    1.03
     thieves
    1.03
     Communists
    1.03
    Activations Density 1.186%

    No Known Activations