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. 9-RES-JB
    6. 11137
    Prev
    Next
    INDEX
    Explanations

    words related to high intensity or strong force

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing strong emotional and physical intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isphere
    -0.92
    士
    -0.81
    DragonMagazine
    -0.81
    ãĥĥãĥĪ
    -0.79
    iland
    -0.77
    wich
    -0.76
    osit
    -0.74
    psc
    -0.73
    uth
    -0.72
    wright
    -0.72
    POSITIVE LOGITS
     bombardment
    0.91
     scrutiny
    0.84
    mble
    0.82
     interrogation
    0.81
     lobbying
    0.81
     heat
    0.81
     intensity
    0.81
     concentration
    0.79
     pressure
    0.78
     intense
    0.78
    Activations Density 0.084%

    No Known Activations