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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17549
    Prev
    Next
    INDEX
    Explanations

    geographical locations or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geographic concepts and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -1.12
    alin
    -1.03
    rin
    -0.88
    enment
    -0.84
    ion
    -0.82
    ework
    -0.80
    nos
    -0.79
    rahim
    -0.79
    ublic
    -0.78
    rentice
    -0.77
    POSITIVE LOGITS
     coordinates
    1.02
     footprint
    0.97
     proximity
    0.89
     geography
    0.88
     boundaries
    0.86
     location
    0.86
     locations
    0.85
     distances
    0.83
     instability
    0.81
     geographic
    0.80
    Activations Density 0.017%

    No Known Activations