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. 0-RES-JB
    6. 8448
    Prev
    Next
    INDEX
    Explanations

    phrases related to rising or increasing actions or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Rise" in various contexts related to events or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gad
    -0.88
     denomin
    -0.84
     colleg
    -0.83
     grocer
    -0.83
     composite
    -0.82
     estab
    -0.82
     taxp
    -0.81
     cler
    -0.81
     vel
    -0.80
     multim
    -0.80
    POSITIVE LOGITS
     Assault
    2.01
     Rise
    1.93
     Shattered
    1.85
     Nightmare
    1.82
     Siege
    1.77
     Murder
    1.75
     Showdown
    1.71
     Darkness
    1.70
     Fallen
    1.69
     Nightmares
    1.69
    Activations Density 0.111%

    No Known Activations