© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20782
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies, regulations, and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social and environmental issues

    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
    confirmed
    -0.70
     Polk
    -0.68
    -+-+
    -0.66
    olen
    -0.65
    Lago
    -0.65
    {"
    -0.65
    uba
    -0.65
    å¸
    -0.64
    verified
    -0.64
    emn
    -0.64
    POSITIVE LOGITS
     debacle
    1.16
     fiasco
    1.09
     phenomenon
    1.08
     program
    1.05
     bandwagon
    1.04
     movement
    1.02
     paradigm
    1.01
     initiative
    1.00
     aspect
    0.99
     industry
    0.99
    Activations Density 0.481%

    No Known Activations