© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1578
    Prev
    Next
    INDEX
    Explanations

    instances where a statement is emphasizing the current time or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "At this point" in various contexts

    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
    ilus
    -0.65
    letters
    -0.62
     drilled
    -0.59
    scape
    -0.59
    keepers
    -0.59
    keeper
    -0.58
    forcing
    -0.58
    bis
    -0.58
    winning
    -0.57
    greg
    -0.57
    POSITIVE LOGITS
     behest
    1.09
     moment
    0.97
     expense
    0.96
     point
    0.96
     level
    0.94
     jun
    0.94
     outset
    0.93
     discretion
    0.93
     conclusion
    0.85
     stage
    0.84
    Activations Density 0.068%

    No Known Activations