© 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. 23874
    Prev
    Next
    INDEX
    Explanations

    references to specific incidents or events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific incidents or events related to law enforcement and investigations

    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
    anol
    -0.63
    mite
    -0.61
    igl
    -0.59
     semblance
    -0.56
    regon
    -0.56
    yrics
    -0.56
     sling
    -0.55
    ĪĴ
    -0.54
    nt
    -0.53
    raviolet
    -0.53
    POSITIVE LOGITS
     beforehand
    0.74
     unfold
    0.73
     involving
    0.64
     happening
    0.62
     occurring
    0.62
     circulated
    0.60
     because
    0.60
     anonymously
    0.60
     firsthand
    0.60
     affecting
    0.60
    Activations Density 0.340%

    No Known Activations