© 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. 7-RES-JB
    11. 11689
    Prev
    Next
    INDEX
    Explanations

    words related to signaling or indicating a significant action or event

    oai_token-act-pair · gpt-3.5-turbo

    phrases that signal significant events or messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consulted
    -0.79
     bathrooms
    -0.66
     motions
    -0.65
     prefers
    -0.65
     diction
    -0.65
     crawling
    -0.64
    tis
    -0.63
     layouts
    -0.63
    responsive
    -0.63
     liking
    -0.62
    POSITIVE LOGITS
     legitim
    0.84
     reminder
    0.78
     culmination
    0.78
     testament
    0.75
    wcs
    0.74
    LEASE
    0.74
     tacit
    0.73
     vind
    0.72
     precedent
    0.72
    entin
    0.71
    Activations Density 1.220%

    No Known Activations