© 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. 6-RES-JB
    11. 2747
    Prev
    Next
    INDEX
    Explanations

    phrases indicating interest or anticipation in future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating anticipation or evaluation of upcoming events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     potential
    -0.61
     culture
    -0.60
    è¦ļéĨĴ
    -0.57
     insin
    -0.57
    ugh
    -0.56
     underworld
    -0.55
    Connector
    -0.55
    ALT
    -0.54
    Property
    -0.54
    Privacy
    -0.54
    POSITIVE LOGITS
     tomorrow
    1.04
     someday
    0.91
     forever
    0.81
    urated
    0.80
    morrow
    0.80
     soon
    0.77
     sooner
    0.76
    rier
    0.75
    ãĥŀ
    0.73
     anytime
    0.70
    Activations Density 0.323%

    No Known Activations