© 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. 12-RES-JB
    11. 3437
    Prev
    Next
    INDEX
    Explanations

    adjectives related to qualities or conditions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to moral and social high grounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Builder
    -0.65
    lished
    -0.63
    nant
    -0.60
     Sidney
    -0.59
    edly
    -0.58
     Bernard
    -0.57
    istar
    -0.56
     Converted
    -0.56
    lde
    -0.55
    aneously
    -0.55
    POSITIVE LOGITS
     spots
    0.80
    NetMessage
    0.79
     hairs
    0.71
    comings
    0.70
    steps
    0.69
    ggles
    0.67
     points
    0.65
     ground
    0.64
     reckoning
    0.63
     patches
    0.63
    Activations Density 0.176%

    No Known Activations