© 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. 6-RES-JB
    11. 14752
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting ideas

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to societal and systemic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    00007
    -0.72
     awoken
    -0.70
    cellaneous
    -0.67
    aspx
    -0.66
    hess
    -0.65
    )))
    -0.65
    Eva
    -0.64
     Nanto
    -0.63
    luck
    -0.61
    aido
    -0.60
    POSITIVE LOGITS
     nor
    1.10
     anymore
    1.02
     necessarily
    0.98
     merely
    0.69
     purely
    0.68
    erker
    0.67
     partisans
    0.67
     altru
    0.64
     partisan
    0.64
     merits
    0.63
    Activations Density 0.938%

    No Known Activations