© 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. 9-RES-JB
    11. 4153
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking an assertive or aggressive stance in a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating strong positions or actions related to conflict or competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aides
    -0.67
     afterward
    -0.65
    amins
    -0.55
    ppings
    -0.53
     stuff
    -0.53
    stuff
    -0.52
    toggle
    -0.52
     toast
    -0.52
     suburb
    -0.51
    UTERS
    -0.51
    POSITIVE LOGITS
     stating
    0.86
     regarding
    0.81
     whilst
    0.80
     ðŁĻĤ
    0.74
     ®
    0.73
     whereby
    0.73
    "]=>
    0.70
     informing
    0.68
     because
    0.66
     Whilst
    0.65
    Activations Density 1.347%

    No Known Activations