© 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. 10-RES-JB
    11. 18958
    Prev
    Next
    INDEX
    Explanations

    mentions of challenges or obstacles associated with specific roles or jobs

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to challenges and accomplishments in various professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     theirs
    -0.72
     accompanying
    -0.70
     redistributed
    -0.69
     indications
    -0.67
     further
    -0.67
     equivalents
    -0.67
     markings
    -0.67
     furthermore
    -0.67
     moreover
    -0.66
     supplying
    -0.65
    POSITIVE LOGITS
     Yourself
    0.90
     yourself
    0.88
     Your
    0.85
     your
    0.79
     oneself
    0.77
    Your
    0.75
     YOUR
    0.70
     WordPress
    0.68
     Survivor
    0.68
     cryptocurrency
    0.68
    Activations Density 0.553%

    No Known Activations