© 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. 18612
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and dialogue

    oai_token-act-pair · gpt-3.5-turbo

    questions or inquiries about the whereabouts of something or someone

    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
    âĢ
    -1.03
    ÂŃ
    -1.01
     ÂŃ
    -0.79
    æ©Ł
    -0.70
    -0.69
    -0.68
    </
    -0.66
    âĢij
    -0.65
    ¶
    -0.65
    åĽ
    -0.64
    POSITIVE LOGITS
     dunno
    0.83
     ;)
    0.77
     :-)
    0.75
     lovely
    0.75
     Stuff
    0.71
    abouts
    0.69
     fav
    0.66
     hipp
    0.65
     rubbish
    0.65
     wee
    0.65
    Activations Density 0.996%

    No Known Activations