© 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. 9-RES-JB
    11. 18342
    Prev
    Next
    INDEX
    Explanations

    phrases related to political debates and statements

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express opinions or remarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     undet
    -0.81
     unlocks
    -0.74
     reversible
    -0.74
    iencies
    -0.72
    versible
    -0.71
     handy
    -0.71
     dips
    -0.71
     unpredict
    -0.69
     fucked
    -0.68
    bolt
    -0.68
    POSITIVE LOGITS
     Others
    1.17
     They
    1.16
     Their
    1.08
     Critics
    1.05
     Specifically
    1.00
     Speaking
    1.00
     Some
    0.99
     Officials
    0.98
     Advoc
    0.98
     Supporters
    0.98
    Activations Density 0.490%

    No Known Activations