© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 423
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations, particularly "Dundee"

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and transportation references

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

    No Comments

    Negative Logits
    stocks
    -0.68
    ularity
    -0.66
    vg
    -0.65
    iquid
    -0.64
    erd
    -0.64
    bub
    -0.64
    nington
    -0.63
     Cosponsors
    -0.63
    jack
    -0.63
    ãģĻ
    -0.62
    POSITIVE LOGITS
     Dund
    1.07
    hesda
    0.85
    ees
    0.83
    rum
    0.79
     Glas
    0.76
    atars
    0.75
    urst
    0.74
    ee
    0.73
    raph
    0.73
    rain
    0.72
    Activations Density 0.025%

    No Known Activations