© 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. 23879
    Prev
    Next
    INDEX
    Explanations

    phrases related to delivery schedules

    oai_token-act-pair · gpt-3.5-turbo

    references to weekday news delivery

    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
    gow
    -0.58
    ère
    -0.57
     plac
    -0.56
     tatt
    -0.56
    abase
    -0.56
     privilege
    -0.55
     enqu
    -0.55
     Paras
    -0.55
     geography
    -0.52
     hive
    -0.52
    POSITIVE LOGITS
     mornings
    0.98
    days
    0.72
    morning
    0.68
    ãĥķ
    0.68
    VER
    0.65
    aturdays
    0.64
    notes
    0.64
    arms
    0.62
     Fridays
    0.62
    iesel
    0.62
    Activations Density 0.043%

    No Known Activations