© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 20477
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the terms "Pac-8" and "Pac-9."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Pac" or related numerical references, likely associated with sports or competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IELD
    -0.79
    UCT
    -0.76
    Charges
    -0.70
     ABE
    -0.69
    âĢ¢âĢ¢
    -0.67
    IGH
    -0.67
    ailed
    -0.65
    IGHTS
    -0.65
     beh
    -0.65
    hower
    -0.64
    POSITIVE LOGITS
    Pac
    1.13
    emaker
    1.09
    ific
    0.90
    achu
    0.90
    IFIC
    0.89
     Pac
    0.88
    anut
    0.88
    rice
    0.86
    atown
    0.84
    itionally
    0.84
    Activations Density 0.015%

    No Known Activations