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. 1-RES-JB
    6. 19829
    Prev
    Next
    INDEX
    Explanations

    references to hydraulic systems or the mythical creature Hydra

    oai_token-act-pair · gpt-3.5-turbo

    references to hydraulic systems and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµ
    -0.76
    \/
    -0.75
    Latin
    -0.73
    çĦ
    -0.71
    ãģĤ
    -0.69
    Interstitial
    -0.68
     âľĵ
    -0.68
    agh
    -0.68
    gdala
    -0.68
    ODUCT
    -0.67
    POSITIVE LOGITS
    ulic
    1.54
     fracturing
    1.44
     hydraulic
    1.24
     fluids
    0.99
     pedals
    0.98
     hydra
    0.95
     earthqu
    0.95
     cylinders
    0.88
     propelled
    0.88
     fluid
    0.86
    Activations Density 0.010%

    No Known Activations