© 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. 10-RES-JB
    11. 15017
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluations, opinions, and conclusions

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing noteworthy or impressive qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unspecified
    -0.80
    illance
    -0.76
    Optional
    -0.75
     mitigation
    -0.73
     withdraw
    -0.73
    Emergency
    -0.71
    ļéĨĴ
    -0.71
    Prosecut
    -0.70
     intervene
    -0.69
     Medicaid
    -0.69
    POSITIVE LOGITS
     legendary
    0.97
     fandom
    0.96
     classics
    0.95
     timeless
    0.95
     greatness
    0.92
     undeniable
    0.90
     legends
    0.90
     countless
    0.89
     genre
    0.89
     humble
    0.89
    Activations Density 0.835%

    No Known Activations