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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 21516
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passing of time or duration

    oai_token-act-pair · gpt-3.5-turbo

    recurring phrases indicating a duration or continuity of discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucker
    -0.69
    interstitial
    -0.67
    ãĥ¯ãĥ³
    -0.65
    DragonMagazine
    -0.63
    AME
    -0.63
    irtual
    -0.62
    ioned
    -0.60
    Champ
    -0.58
    opal
    -0.58
    iop
    -0.58
    POSITIVE LOGITS
     awhile
    1.40
     years
    1.31
     decades
    1.29
     ages
    1.25
     centuries
    1.20
     quite
    1.19
     YEAR
    1.17
     months
    1.16
     millennia
    1.15
     generations
    1.13
    Activations Density 0.063%

    No Known Activations