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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 14528
    Prev
    Next
    INDEX
    Explanations

    phrases related to research methodology and ethical conduct

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to wealth and value generation

    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
    independent
    -0.56
    hower
    -0.55
    quarter
    -0.53
    international
    -0.52
    intendent
    -0.52
     toget
    -0.51
     TheNitromeFan
    -0.51
    theless
    -0.51
    conserv
    -0.51
     storm
    -0.49
    POSITIVE LOGITS
     Products
    0.68
     Simulator
    0.67
     Disorder
    0.66
     Ltd
    0.65
     Guys
    0.65
     Than
    0.64
     Machines
    0.64
     Complex
    0.63
     Caps
    0.63
    earances
    0.63
    Activations Density 0.886%

    No Known Activations