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. 11-RES-JB
    6. 22912
    Prev
    Next
    INDEX
    Explanations

    locations or institutions in different cities worldwide

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" indicating locations or contexts within sentences

    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
    DragonMagazine
    -0.80
     accordingly
    -0.74
    AMY
    -0.71
    untled
    -0.69
    ĺħ
    -0.68
     gaping
    -0.65
     sooner
    -0.65
     innoc
    -0.64
     performers
    -0.64
    pace
    -0.64
    POSITIVE LOGITS
     conjunction
    1.24
     collaboration
    1.13
     Washington
    1.12
     partnership
    1.10
     Charge
    1.09
     London
    1.06
     Canberra
    1.06
     charge
    1.05
     Arlington
    1.04
     Geneva
    1.03
    Activations Density 0.128%

    No Known Activations