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. 1-RES-JB
    6. 17843
    Prev
    Next
    INDEX
    Explanations

    words ending in 'cent' or 'center'

    oai_token-act-pair · gpt-3.5-turbo

    references to central themes or ideas in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.78
     ABE
    -0.77
    é¾įå
    -0.70
     Tycoon
    -0.68
    éĹĺ
    -0.67
    isSpecialOrderable
    -0.65
    HCR
    -0.64
    lished
    -0.64
     OC
    -0.64
    HEAD
    -0.63
    POSITIVE LOGITS
    enary
    1.06
    imeters
    1.04
    cent
    1.00
    imeter
    0.99
    rils
    0.94
    rals
    0.90
    imet
    0.89
    uries
    0.86
    rity
    0.84
    ennial
    0.83
    Activations Density 0.007%

    No Known Activations