© 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. 9-RES-JB
    11. 11384
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations and events

    oai_token-act-pair · gpt-3.5-turbo

    references to cities and geographic locations in relation to events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realise
    -1.04
     organise
    -1.04
     flavours
    -1.04
     favourites
    -1.02
     recognise
    -1.01
     organis
    -0.97
     flavour
    -0.94
     maths
    -0.94
     realised
    -0.93
     behaviours
    -0.93
    POSITIVE LOGITS
    Hispanic
    0.75
    Copyright
    0.75
     Sioux
    0.71
    arcer
    0.70
     Hispanic
    0.70
    Native
    0.69
    Ohio
    0.69
    aukee
    0.69
     Native
    0.68
     honoring
    0.68
    Activations Density 1.665%

    No Known Activations