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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14439
    Prev
    Next
    INDEX
    Explanations

    mentions of heightened situations or emotions

    oai_token-act-pair · gpt-3.5-turbo

    references to heightened situations or conditions, particularly concerning tensions and emergencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Papers
    -0.73
     spoiler
    -0.64
    etitive
    -0.62
     tract
    -0.61
     disk
    -0.61
     scars
    -0.60
     diamond
    -0.59
     corrid
    -0.59
    ression
    -0.59
     graft
    -0.58
    POSITIVE LOGITS
    isson
    0.89
    ween
    0.87
    USS
    0.83
    ignty
    0.78
     Lumpur
    0.75
    ivities
    0.72
    orne
    0.71
    OME
    0.70
     guiActiveUn
    0.70
    CHR
    0.70
    Activations Density 0.034%

    No Known Activations