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. 11-RES-JB
    6. 8746
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the Dutch and the Netherlands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilitating
    -0.69
    uating
    -0.68
    natureconservancy
    -0.68
    vae
    -0.66
     Tsu
    -0.66
    icago
    -0.66
     nerv
    -0.65
    zona
    -0.65
    ologies
    -0.64
     Hussain
    -0.64
    POSITIVE LOGITS
    ijk
    1.11
     Netherlands
    1.04
    sterdam
    0.93
    lander
    0.91
     Indies
    0.89
    ijn
    0.88
    borg
    0.87
    mans
    0.86
     Amsterdam
    0.85
    man
    0.82
    Activations Density 0.053%

    No Known Activations