© 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. 2877
    Prev
    Next
    INDEX
    Explanations

    instances of the word "recent"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "recent."

    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
    antry
    -0.74
    ette
    -0.70
     becomes
    -0.68
    uten
    -0.67
    ettes
    -0.66
    $$$$
    -0.66
     ends
    -0.66
     Again
    -0.64
    ulum
    -0.60
     governed
    -0.59
    POSITIVE LOGITS
     recent
    3.36
    recent
    2.51
    Recent
    1.99
     Recent
    1.93
     recently
    1.88
     lately
    1.58
     previous
    1.57
    Recently
    1.57
     latest
    1.53
     Recently
    1.47
    Activations Density 0.026%

    No Known Activations