© 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. 4-RES-JB
    11. 18054
    Prev
    Next
    INDEX
    Explanations

    verbs related to predicting or foreseeing future events or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    words related to expectation and prediction

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

    No Comments

    Negative Logits
    undy
    -0.73
    bard
    -0.72
    ldon
    -0.70
    gars
    -0.68
    yards
    -0.67
    eled
    -0.67
    gar
    -0.66
    bag
    -0.65
     Compact
    -0.64
    oard
    -0.64
    POSITIVE LOGITS
     anticipation
    0.87
     anticipate
    0.85
     anticipating
    0.83
    ROR
    0.82
     anticip
    0.81
     foresee
    0.78
     anticipated
    0.78
     Lauder
    0.73
    WER
    0.71
    eers
    0.69
    Activations Density 0.011%

    No Known Activations