© 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 EvalsExportsinterp-engineNEWAPI 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. 13251
    Prev
    Next
    INDEX
    Explanations

    phrases related to choices or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases or items related to conditional or alternative scenarios

    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
     creep
    -0.73
     warr
    -0.68
     stalking
    -0.68
     Dug
    -0.64
    atche
    -0.63
     accus
    -0.63
     Moody
    -0.63
     Fletcher
    -0.63
     Arabian
    -0.62
     disgu
    -0.62
    POSITIVE LOGITS
    etc
    1.29
    pmwiki
    1.03
    1000
    1.02
    whatever
    1.02
    AFP
    0.98
    Getty
    0.97
    2014
    0.97
    CN
    0.96
    2011
    0.96
    2012
    0.95
    Activations Density 0.098%

    No Known Activations