© 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. 10-RES-JB
    11. 18960
    Prev
    Next
    INDEX
    Explanations

    descriptions of urban environments and transportation infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to infrastructure and pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omatic
    -0.61
    rogram
    -0.61
    ulz
    -0.61
    Os
    -0.60
    ãĥīãĥ©
    -0.60
     Dollars
    -0.59
    Flight
    -0.59
     CES
    -0.57
     DVDs
    -0.56
     iTunes
    -0.56
    POSITIVE LOGITS
     overlooking
    1.27
     separating
    1.22
     dividing
    1.12
     entrance
    1.12
     junction
    1.11
     overlook
    1.07
     slope
    1.07
     fence
    1.06
     ledge
    1.06
     adjacent
    1.05
    Activations Density 0.258%

    No Known Activations