© 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. 3162
    Prev
    Next
    INDEX
    Explanations

    references to financial support

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

    the word "supp" in various contexts

    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
     intimidating
    -0.68
     punitive
    -0.67
     Warsaw
    -0.61
     behavi
    -0.61
     colonial
    -0.60
     contempt
    -0.60
     defamation
    -0.60
     adultery
    -0.59
     bureaucratic
    -0.59
     foul
    -0.58
    POSITIVE LOGITS
    lied
    1.67
    orters
    1.66
    orter
    1.65
    ression
    1.54
    lication
    1.53
    osed
    1.50
    orts
    1.49
    lying
    1.46
    lier
    1.44
    ressive
    1.44
    Activations Density 0.013%

    No Known Activations