© 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. 10-RES-JB
    11. 13817
    Prev
    Next
    INDEX
    Explanations

    comparisons related to expectations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote expectations or comparisons of perceived reality versus prior assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attm
    -0.61
     heterogeneity
    -0.60
    mary
    -0.58
     Rolls
    -0.58
     Weak
    -0.57
     Links
    -0.56
     Presence
    -0.55
     Viol
    -0.55
     Surveillance
    -0.55
     Vine
    -0.54
    POSITIVE LOGITS
     imagined
    1.36
     anticipated
    1.35
     expected
    1.21
     envisioned
    1.17
    expected
    1.17
     hoped
    1.06
     remembered
    1.05
     dreamed
    1.02
     envis
    1.02
     guessed
    1.02
    Activations Density 0.143%

    No Known Activations