© 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. 14022
    Prev
    Next
    INDEX
    Explanations

    words related to significant, impactful events or actions, such as "move," "collapse," "attack," "remake," "crash," and "assassination."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to potential actions and events, particularly in political and military 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
    itudes
    -0.73
    ongs
    -0.72
    verbs
    -0.72
     newsletters
    -0.68
     pupils
    -0.66
     merchants
    -0.62
     virtues
    -0.62
     neighbourhoods
    -0.61
    cled
    -0.61
     banners
    -0.61
    POSITIVE LOGITS
     someday
    1.04
     showdown
    0.93
     sooner
    0.87
     anytime
    0.82
     ASAP
    0.80
    breaker
    0.80
    urrence
    0.78
     akin
    0.77
    peat
    0.76
    cation
    0.75
    Activations Density 0.364%

    No Known Activations