© 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. 9-RES-JB
    11. 8652
    Prev
    Next
    INDEX
    Explanations

    phrases related to names of products or organizations

    oai_token-act-pair · gpt-3.5-turbo

    periods and punctuation at the end of sentences

    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
     allowance
    -0.78
     tyr
    -0.71
     affili
    -0.71
     suspic
    -0.67
     regenerate
    -0.66
     elbows
    -0.65
     temperament
    -0.65
     absentee
    -0.65
     confir
    -0.63
     regeneration
    -0.63
    POSITIVE LOGITS
     Essentially
    1.37
     Featuring
    1.28
     Basically
    1.25
     Originally
    1.23
     Located
    1.22
     Though
    1.19
     Designed
    1.19
     Created
    1.19
     Released
    1.19
     Whereas
    1.16
    Activations Density 0.353%

    No Known Activations