© 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. 11-RES-JB
    11. 5746
    Prev
    Next
    INDEX
    Explanations

    phrases indicating updates or news

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory statements and expressions of enthusiasm or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     predis
    -0.83
     differentiated
    -0.74
     disadvantage
    -0.71
     distinguished
    -0.71
     minim
    -0.71
     exerted
    -0.70
     contextual
    -0.70
     distinguish
    -0.70
     disadvantages
    -0.69
     challeng
    -0.69
    POSITIVE LOGITS
    Yesterday
    1.30
     Yesterday
    1.23
    Tonight
    1.17
    Today
    1.09
    Firstly
    1.08
    Hello
    1.06
     Tonight
    1.05
    Congratulations
    1.04
    Tomorrow
    1.04
    TOR
    1.01
    Activations Density 0.560%

    No Known Activations