© 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. 3544
    Prev
    Next
    INDEX
    Explanations

    associations between different concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to causal and correlational relationships

    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
     Reserved
    -0.68
    lite
    -0.66
     Surv
    -0.61
    EMS
    -0.59
    DIV
    -0.58
    OWN
    -0.58
    FAQ
    -0.58
    oway
    -0.58
     composure
    -0.58
    skirts
    -0.57
    POSITIVE LOGITS
     between
    1.58
    between
    1.37
     Between
    1.23
     linking
    1.03
     BET
    0.98
    ages
    0.95
    uality
    0.90
     connecting
    0.90
     coefficient
    0.85
    ality
    0.83
    Activations Density 0.084%

    No Known Activations