Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14485
    Prev
    Next
    INDEX
    Explanations

    the word "kitten" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "written" and related terms

    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
     distingu
    -0.76
    Ͻ
    -0.74
    ModLoader
    -0.72
    arta
    -0.71
    BILITY
    -0.69
     surv
    -0.69
     disadvantages
    -0.69
    awaru
    -0.68
    rimination
    -0.66
     simultane
    -0.66
    POSITIVE LOGITS
    itten
    0.81
     Craw
    0.80
     Yankee
    0.76
    combe
    0.76
     GIF
    0.76
    bats
    0.74
    zees
    0.74
    acht
    0.73
    burg
    0.72
    ches
    0.72
    Activations Density 0.007%

    No Known Activations