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. 2-RES-JB
    6. 20035
    Prev
    Next
    INDEX
    Explanations

    words related to a performance stage

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "stage"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.70
    anguages
    -0.70
    £ı
    -0.68
    alez
    -0.67
    uyomi
    -0.67
    olulu
    -0.65
     unequ
    -0.65
    uala
    -0.64
     newcom
    -0.63
    umar
    -0.62
    POSITIVE LOGITS
     stage
    0.91
    Stage
    0.90
    craft
    0.87
    stage
    0.83
     Stage
    0.77
     Sabha
    0.77
    yard
    0.76
    wright
    0.71
    ctrl
    0.68
     stages
    0.68
    Activations Density 0.012%

    No Known Activations