© 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. 9874
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the duration of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of duration or continuity

    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
    onomy
    -0.60
    Ĥİ
    -0.59
    atem
    -0.57
     [&
    -0.55
     Gospel
    -0.53
    £ı
    -0.53
    ãĥ©ãĥ³
    -0.52
    catentry
    -0.52
    Gaza
    -0.51
    aintain
    -0.51
    POSITIVE LOGITS
     anymore
    1.23
     terribly
    1.22
     much
    1.21
    much
    1.05
     too
    1.03
     very
    1.02
     quite
    0.97
     MUCH
    0.92
     any
    0.91
    quite
    0.88
    Activations Density 0.262%

    No Known Activations