© 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. 9955
    Prev
    Next
    INDEX
    Explanations

    mention uses of the word "will" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "will" indicating intention or future actions

    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
    amps
    -0.65
    amped
    -0.65
    BuyableInstoreAndOnline
    -0.65
    quickShipAvailable
    -0.64
    REE
    -0.64
    Creat
    -0.63
    bies
    -0.63
    angled
    -0.63
    uria
    -0.62
    taboola
    -0.62
    POSITIVE LOGITS
     gladly
    1.32
     admit
    0.98
     assume
    0.98
     presume
    0.93
     happily
    0.93
     continue
    0.92
     summarize
    0.91
     endeavour
    0.91
     reiterate
    0.89
     discuss
    0.87
    Activations Density 0.095%

    No Known Activations