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. 10-RES-JB
    6. 15297
    Prev
    Next
    INDEX
    Explanations

    government agencies and political figures related to foreign affairs and intelligence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government, intelligence, and foreign affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alos
    -0.74
    INAL
    -0.72
    ongevity
    -0.71
     "$:/
    -0.71
    devices
    -0.69
    Sequ
    -0.69
    Cooldown
    -0.68
    Moore
    -0.67
    issan
    -0.66
    Portland
    -0.64
    POSITIVE LOGITS
     embassies
    0.90
     diplomats
    0.84
     abroad
    0.84
     embassy
    0.83
     Lavrov
    0.82
     medd
    0.81
     ambassador
    0.80
     envoy
    0.77
     espionage
    0.77
     deleg
    0.76
    Activations Density 0.076%

    No Known Activations