© 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. 3275
    Prev
    Next
    INDEX
    Explanations

    self-affirming, motivational phrases

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

    supportive and motivational statements regarding self-identity and belonging

    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
    SPONSORED
    -0.70
     suggest
    -0.68
     Hera
    -0.67
     suggested
    -0.60
    romptu
    -0.58
     foresee
    -0.58
     observable
    -0.58
     staggered
    -0.58
     correspond
    -0.57
     interchange
    -0.57
    POSITIVE LOGITS
    âĢ
    1.33
    ðŁij
    1.08
    ðŁ
    1.05
     âĢ
    1.04
    âĿ
    1.03
    âĺ
    1.00
     ðŁij
    1.00
    âľ
    1.00
    !.
    1.00
    âĻ
    0.99
    Activations Density 0.781%

    No Known Activations