© 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. 3843
    Prev
    Next
    INDEX
    Explanations

    actions and outcomes related to performance and success

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

    actions or performance evaluations related to various subjects or entities

    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
    ithing
    -0.79
    eros
    -0.78
    ibi
    -0.74
    urrent
    -0.72
    ython
    -0.69
    rador
    -0.68
    ritical
    -0.68
    edia
    -0.66
    ulent
    -0.66
    ļéĨĴ
    -0.65
    POSITIVE LOGITS
     well
    1.86
     poorly
    1.56
     nicely
    1.44
     wonderfully
    1.40
     brilliantly
    1.40
     beautifully
    1.39
     exceptionally
    1.35
     perfectly
    1.34
    well
    1.31
     fine
    1.30
    Activations Density 0.426%

    No Known Activations