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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11184
    Prev
    Next
    INDEX
    Explanations

    codes or indications of the best choice or value

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "best" and high-quality rankings

    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
     notice
    -0.70
     circum
    -0.66
     Nixon
    -0.65
     Pastebin
    -0.63
     admissions
    -0.62
    gered
    -0.61
     Sub
    -0.61
     eaves
    -0.60
     Nin
    -0.60
     phr
    -0.59
    POSITIVE LOGITS
    Best
    3.60
    best
    1.99
    Favorite
    1.51
    Excellent
    1.48
    Winner
    1.44
     Best
    1.43
    Better
    1.39
     BEST
    1.37
    Awesome
    1.35
    Love
    1.32
    Activations Density 0.017%

    No Known Activations