© 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. 0-RES-JB
    11. 22541
    Prev
    Next
    INDEX
    Explanations

    the word "afterwards"

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods or events that occur after a specific moment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nic
    -0.67
    arth
    -0.57
     fiscal
    -0.55
    iane
    -0.54
     License
    -0.53
     Posted
    -0.53
     decentralized
    -0.52
    reetings
    -0.52
     latitude
    -0.51
     Integrated
    -0.51
    POSITIVE LOGITS
     afterwards
    3.76
     afterward
    3.53
     thereafter
    2.64
     Afterwards
    2.10
     beforehand
    2.06
     later
    1.72
     subsequently
    1.45
    later
    1.43
     subsequent
    1.35
     Later
    1.26
    Activations Density 0.004%

    No Known Activations