© 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. 4-RES-JB
    11. 10209
    Prev
    Next
    INDEX
    Explanations

    instances of the word "continuity" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to continuity in narratives or events

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

    No Comments

    Negative Logits
    ª
    -0.74
    gress
    -0.72
    bern
    -0.71
    ij
    -0.71
    uned
    -0.71
    Interstitial
    -0.71
    heimer
    -0.71
    «
    -0.70
    mann
    -0.68
    sf
    -0.68
    POSITIVE LOGITS
     continuity
    1.02
    icity
    0.89
     continuum
    0.84
    uity
    0.76
     compatibility
    0.75
    iversal
    0.75
     mismatch
    0.74
     parity
    0.74
    uality
    0.74
     connectivity
    0.74
    Activations Density 0.030%

    No Known Activations