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. 7869
    Prev
    Next
    INDEX
    Explanations

    the string "orn" followed by either a number 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the name 'Korn' or its variations in different 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
     Pwr
    -0.80
    dule
    -0.70
     intuitive
    -0.69
    arnaev
    -0.68
    aeper
    -0.65
     fact
    -0.64
    amins
    -0.63
    tem
    -0.63
    pton
    -0.61
     convenient
    -0.60
    POSITIVE LOGITS
    orn
    1.17
    obyl
    0.86
    ORN
    0.86
    odon
    0.84
    ication
    0.79
    alia
    0.78
     Torn
    0.77
     Gleaming
    0.75
    OGR
    0.75
    ography
    0.72
    Activations Density 0.007%

    No Known Activations