© 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. 9-RES-JB
    11. 8846
    Prev
    Next
    INDEX
    Explanations

    mentions of high expectations or speculations regarding future outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to expectations and their high or low implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mans
    -0.73
    vertisement
    -0.69
    packing
    -0.68
    stocks
    -0.68
    Ay
    -0.67
    tan
    -0.67
    ners
    -0.66
    wick
    -0.66
    harm
    -0.66
    ston
    -0.65
    POSITIVE LOGITS
     expectations
    0.92
     expectation
    0.78
     cooker
    0.75
     ceilings
    0.73
    ariat
    0.70
    wcsstore
    0.69
     regarding
    0.67
     fulfilled
    0.66
    inen
    0.65
    oft
    0.65
    Activations Density 0.051%

    No Known Activations