© 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. 1387
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or terms related to "Keeping"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "keeping"

    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
    Merit
    -0.72
    Interstitial
    -0.71
    OUN
    -0.70
    emphasis
    -0.68
    çīĪ
    -0.63
    NetMessage
    -0.62
    NRS
    -0.62
     Bowen
    -0.61
    lik
    -0.59
     Jed
    -0.59
    POSITIVE LOGITS
     tabs
    0.95
     pace
    0.87
     track
    0.83
     afloat
    0.83
    keeping
    0.80
     vigil
    0.80
     alive
    0.75
    tracks
    0.73
     conserv
    0.72
     keeping
    0.69
    Activations Density 0.009%

    No Known Activations