© 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. 20711
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    references to paths or journeys

    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
    lishes
    -0.68
     actionGroup
    -0.65
    iston
    -0.65
     artif
    -0.64
    esson
    -0.60
    onom
    -0.60
     pse
    -0.59
     Artificial
    -0.59
    cons
    -0.58
    unn
    -0.58
    POSITIVE LOGITS
     home
    1.41
    packing
    0.98
    home
    0.97
     Home
    0.96
     HOME
    0.94
     downstairs
    0.92
     west
    0.89
     back
    0.87
     thence
    0.86
     north
    0.86
    Activations Density 0.228%

    No Known Activations