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. 9911
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or areas, especially those inhabited by communities or with specific landmarks

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and the communities associated with them

    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
     DOJ
    -0.69
     FOIA
    -0.68
     McCabe
    -0.65
    apple
    -0.65
    xon
    -0.65
     DOD
    -0.63
     Conway
    -0.62
    Adams
    -0.62
    Todd
    -0.62
    pard
    -0.62
    POSITIVE LOGITS
     labou
    0.93
     Rohing
    0.86
     Yuan
    0.80
     organise
    0.77
     villagers
    0.74
     Rohingya
    0.74
     å¤
    0.74
     organising
    0.71
     Tanz
    0.71
    ÅĤ
    0.71
    Activations Density 1.221%

    No Known Activations