Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14987
    Prev
    Next
    INDEX
    Explanations

    terms related to geography and spatial location

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geography and spatial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rin
    -0.96
    alin
    -0.95
    lain
    -0.94
    ride
    -0.80
    nen
    -0.79
    amina
    -0.79
    enment
    -0.79
    ublic
    -0.76
    nos
    -0.76
    ra
    -0.76
    POSITIVE LOGITS
     geographically
    0.96
     geography
    0.94
     footprint
    0.93
     boundaries
    0.86
     geographic
    0.85
     coordinates
    0.82
     proximity
    0.79
     geographical
    0.79
     disadvantage
    0.79
     illiter
    0.77
    Activations Density 0.014%

    No Known Activations