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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19384
    Prev
    Next
    INDEX
    Explanations

    references to locations, specifically focusing on the city of Cardiff

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations, particularly cities and programming libraries

    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
    cham
    -0.69
    ebin
    -0.65
     embr
    -0.64
    elman
    -0.64
    galitarian
    -0.63
     Gamergate
    -0.63
    ntil
    -0.62
    ESH
    -0.61
    earing
    -0.61
    lasses
    -0.61
    POSITIVE LOGITS
    angelo
    0.82
     Coliseum
    0.75
    iana
    0.71
    ulla
    0.69
    backs
    0.69
    iance
    0.66
    ids
    0.65
    idian
    0.65
     Dhabi
    0.65
    allion
    0.65
    Activations Density 0.017%

    No Known Activations