© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 23471
    Prev
    Next
    INDEX
    Explanations

    the word "expect"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate expectations or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matter
    -0.71
    reen
    -0.68
    amic
    -0.68
    pmwiki
    -0.65
    cit
    -0.65
    pi
    -0.61
    program
    -0.61
    clear
    -0.61
    agra
    -0.60
    conscious
    -0.60
    POSITIVE LOGITS
     expect
    0.87
    ebus
    0.79
    terson
    0.73
     expects
    0.72
    tower
    0.68
    ĭ
    0.68
     expectations
    0.67
    eur
    0.66
    ãĥĻ
    0.65
     vulner
    0.65
    Activations Density 0.025%

    No Known Activations