© 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. 2-RES-JB
    11. 24101
    Prev
    Next
    INDEX
    Explanations

    instances of the word "anticipate" in text

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to expecting or predicting future events

    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
    bard
    -0.78
    agra
    -0.75
    unal
    -0.71
    eled
    -0.71
    anski
    -0.69
    ldon
    -0.68
    borg
    -0.68
    ggies
    -0.68
    adra
    -0.67
    phy
    -0.67
    POSITIVE LOGITS
     anticipation
    1.04
     anticip
    1.02
     anticipate
    0.95
     anticipating
    0.94
     anticipated
    0.84
     foresee
    0.82
     Lauder
    0.76
     predicts
    0.74
    ROR
    0.72
    WER
    0.71
    Activations Density 0.008%

    No Known Activations