© 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. 9-RES-JB
    11. 15427
    Prev
    Next
    INDEX
    Explanations

    verbs indicating persistence or survival

    oai_token-act-pair · gpt-3.5-turbo

    terms related to survival and current status in various contexts

    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
     sooner
    -0.71
     earlier
    -0.67
    zsche
    -0.67
    roid
    -0.66
    hes
    -0.65
    har
    -0.63
     THEN
    -0.62
     Begins
    -0.61
     later
    -0.61
     mattered
    -0.60
    POSITIVE LOGITS
     now
    1.02
     currently
    1.01
    currently
    0.94
     presently
    0.86
    now
    0.70
     Currently
    0.68
     NOW
    0.67
    Currently
    0.66
     awaiting
    0.65
     pending
    0.62
    Activations Density 1.150%

    No Known Activations