© 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. 5675
    Prev
    Next
    INDEX
    Explanations

    past tense verbs in the context of events or actions that were never completed

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "never."

    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
    ahime
    -0.93
    pour
    -0.88
     antioxid
    -0.84
    iant
    -0.69
    tein
    -0.66
    achev
    -0.66
     Tags
    -0.63
    åĤ
    -0.61
    imo
    -0.61
    emia
    -0.60
    POSITIVE LOGITS
    theless
    1.74
     bothered
    1.16
     ceases
    1.06
     dreamed
    1.01
    mind
    0.97
     bothers
    0.92
     ceased
    0.90
     imagined
    0.89
     EVER
    0.87
     heard
    0.85
    Activations Density 0.057%

    No Known Activations